F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration | Paper Citation Record

Observation 2de9686a-2f86-4450-a012-caefdc1128fa · outbound

This paper cites an unresolved cited work.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.072867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3e7d876-274b-44d8-9e62-8d7b78cf7738 · outbound

This paper cites co / dreamlike - art / dreamlike - photoreal - 2.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration co / dreamlike - art / dreamlike - photoreal - 2

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.081078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157288c8-5da5-416d-ab37-9dfd1297211d · outbound

This paper cites co / black - forest-labs/FLUX.1-dev, Accessed: 2024-10-03.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration co / black - forest-labs/FLUX.1-dev, Accessed: 2024-10-03

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.087297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bef6a3e2-3da2-4a74-8264-034fd9e04123 · outbound

This paper cites co/h94/IP-Adapter, Accessed: 2024-10-03.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration co/h94/IP-Adapter, Accessed: 2024-10-03

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.092870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 171f68c5-e5d1-43c0-b7da-8632e876d174 · outbound

This paper cites co/h94/IP-Adapter-FaceID, Accessed: 2024-10-.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration co/h94/IP-Adapter-FaceID, Accessed: 2024-10-

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.098397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6676abdf-718a-4581-92d0-75f8d0714d70 · outbound

This paper cites co / Kwai - Kolors/Kolors, Accessed: 2024-10-03.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration co / Kwai - Kolors/Kolors, Accessed: 2024-10-03

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.104129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 359787bd-ee3f-4627-aeea-db45de070270 · outbound

This paper cites co / stablediffusionapi/protovision- xl- v6.6, Accessed: 2024-10-03.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration co / stablediffusionapi/protovision- xl- v6.6, Accessed: 2024-10-03

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.110322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16bebdc-42a5-47aa-b202-49273b8e08f7 · outbound

This paper cites 3, 5, 1, 4.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration 3, 5, 1, 4

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.115662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43ca714c-5f8f-46b0-814f-4c6d5904a5ea · outbound

This paper cites an unresolved cited work.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.121105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2152b3ad-150c-4d1c-9140-1cf77bdcf575 · outbound

This paper cites an unresolved cited work.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.126784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76c6e475-906a-413d-8f11-75cbc3c47e18 · outbound

This paper cites Qwen2.5-VL Technical Report.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Qwen2.5-VL Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.132323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887537d0-e34a-4d38-93d2-0f2cad11bef4 · outbound

This paper cites Cr-fiqa: face image quality assessment by learning sample relative classifiability.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Cr-fiqa: face image quality assessment by learning sample relative classifiability

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.138285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b836aa07-91fb-4ce5-8cba-088fe8ca22ff · outbound

This paper cites An image quality assessment dataset for portraits.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration An image quality assessment dataset for portraits

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.143210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a6d98f-c923-48bd-a1a5-89f36d3bd8a1 · outbound

This paper cites Promptiqa: Boosting the performance and gen- eralization for no-reference image quality assessment via prompts.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Promptiqa: Boosting the performance and gen- eralization for no-reference image quality assessment via prompts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.148301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a1f55d-2c2f-4d41-a928-37b81d2a9a25 · outbound

This paper cites Learning spatial attention for face super-resolution.IEEE Transactions on Image Processing (TIP), 30:1219–1231, 2020.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Learning spatial attention for face super-resolution.IEEE Transactions on Image Processing (TIP), 30:1219–1231, 2020

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.153338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f5bd37-cf69-49a5-8c0f-4a8074e1d41e · outbound

This paper cites Progressive semantic- aware style transformation for blind face restoration.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Progressive semantic- aware style transformation for blind face restoration

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.158725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec2f03e-cd29-4fad-a54d-58b92aedd931 · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.164313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c21e3ab1-96a1-48af-88a1-d9bdc2c1c3c7 · outbound

This paper cites Dsl-fiqa: Assess- ing facial image quality via dual-set degradation learning and landmark-guided transformer.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Dsl-fiqa: Assess- ing facial image quality via dual-set degradation learning and landmark-guided transformer

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.170301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21b0591a-7360-4d0e-a855-0036aeaf0ae3 · outbound

This paper cites Fsrnet: End-to-end learning face super-resolution with facial priors.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Fsrnet: End-to-end learning face super-resolution with facial priors

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.175598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce0fdeb-2a76-403d-8e12-961fa919e0fc · outbound

This paper cites IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.180191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36f4a836-f726-404c-8b99-dbcf3efaa28f · outbound

This paper cites Flashattention-2: Faster attention with better par- allelism and work partitioning.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Flashattention-2: Faster attention with better par- allelism and work partitioning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.185040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1ecfb00-e557-406a-8a73-23f9dc2dcc07 · outbound

This paper cites Arcface: Additive angular margin loss for deep face recognition.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Arcface: Additive angular margin loss for deep face recognition

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.189951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6f2527-da00-4c32-b93c-b3d7ab2bab19 · outbound

This paper cites Finevq: Fine-grained user generated content video quality assessment.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Finevq: Fine-grained user generated content video quality assessment

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.194470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12915a5e-a520-4178-a38e-8694487ae30a · outbound

This paper cites An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.198955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4e2a0b5-c75c-4b29-942c-d477438ecb43 · outbound

This paper cites Alireza Golestaneh, Saba Dadsetan, and Kris M.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Alireza Golestaneh, Saba Dadsetan, and Kris M

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.203788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9908a2-17bb-4faf-bb1d-649cbf889a96 · outbound

This paper cites Generative adversarial nets.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Generative adversarial nets

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.208664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47cfa1d-72dd-4706-9dd0-a361a6bb03a4 · outbound

This paper cites Fisblim: A five-step blind metric for quality assessment of multiply distorted images.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Fisblim: A five-step blind metric for quality assessment of multiply distorted images

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.213253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3043b9b5-8322-4f16-b8aa-0f3f36b50645 · outbound

This paper cites VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.218008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d6e0406-e0a3-4a1d-b357-6aef6d034199 · outbound

This paper cites Deep residual learning for image recognition.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Deep residual learning for image recognition

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.223535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75b86ceb-ac4a-428f-9a24-e79fde513a97 · outbound

This paper cites ID-Animator: Zero-Shot Identity-Preserving Human Video Generation.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration ID-Animator: Zero-Shot Identity-Preserving Human Video Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.228261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e507a53-1dfb-4f33-8ca4-7c97ca5345f3 · outbound

This paper cites Faceqnet: Quality assessment for face recognition based on deep learning.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Faceqnet: Quality assessment for face recognition based on deep learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.233244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e674d951-f96c-4053-9cc5-eafd2b5d6599 · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.237758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb5b75fa-9eae-4412-be42-4dd606ac57c2 · outbound

This paper cites Denoising dif- fusion probabilistic models.Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 33: 6840–6851, 2020.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Denoising dif- fusion probabilistic models.Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 33: 6840–6851, 2020

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.242427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e3d9385-c9a5-465f-8c11-17f194a870b6 · outbound

This paper cites Image quality metrics: Psnr vs.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Image quality metrics: Psnr vs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.247056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fad82be-a3cd-45ad-9fde-c3d9d670371d · outbound

This paper cites Lora: Low- rank adaptation of large language models.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Lora: Low- rank adaptation of large language models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.251615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f96c54e3-1763-4f17-b63e-735b5b8ac6cf · outbound

This paper cites Varfvv: View- adaptive real-time interactive free-view video streaming with edge computing.IEEE Journal on Selected Areas in Communications, 2025.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Varfvv: View- adaptive real-time interactive free-view video streaming with edge computing.IEEE Journal on Selected Areas in Communications, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.256136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc8f7c8-960c-4f54-a7c4-d95cfc56ebe3 · outbound

This paper cites 4dgc: Rate-aware 4d gaussian compression for efficient streamable free-viewpoint video.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration 4dgc: Rate-aware 4d gaussian compression for efficient streamable free-viewpoint video

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.260536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14638eb4-2d75-4abe-9e3e-b520e20e22c7 · outbound

This paper cites Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.265019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 585cde9a-cc47-4199-ade4-b7a49ff3522b · outbound

This paper cites an unresolved cited work.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.269620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f85184b0-3ca5-4243-8b46-79a54bd882ca · outbound

This paper cites Catekv: On sequential consistency for long-context llm inference acceleration.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Catekv: On sequential consistency for long-context llm inference acceleration

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.274365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc78bd49-14b6-4ad4-bf7c-0015c979138c · outbound

This paper cites Ifqa: Interpretable face quality assessment.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Ifqa: Interpretable face quality assessment

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.278975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35ae30a-2e70-4798-a26d-a4d8638ccb7e · outbound

This paper cites Convo- lutional neural networks for no-reference image quality as- sessment.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Convo- lutional neural networks for no-reference image quality as- sessment

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.283814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc92b4ee-beed-46c6-b9d7-678bf868e447 · outbound

This paper cites A style-based generator architecture for generative adversarial networks.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration A style-based generator architecture for generative adversarial networks

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.288373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 857382f2-a8b3-4c51-991d-fee616764dc0 · outbound

This paper cites Imagic: Text-based real image editing with diffusion mod- els.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Imagic: Text-based real image editing with diffusion mod- els

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.293124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52843336-8489-411c-93b9-a65034e3fa96 · outbound

This paper cites The megaface benchmark: 1 million faces for recognition at scale.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration The megaface benchmark: 1 million faces for recognition at scale

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.179397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1a958f52-a223-41ab-9f21-09f7629f1a6b · outbound

This paper cites Progressive Face Super-Resolution via Attention to Facial Landmark.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Progressive Face Super-Resolution via Attention to Facial Landmark

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.302057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 684fd1b8-d0d7-4876-96a1-aa1899e84fba · outbound

This paper cites Auto-encoding variational bayes.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Auto-encoding variational bayes

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.164254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation de25b419-b2fe-4198-9b3d-6710ea795323 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Pick-a-pic: An open dataset of user preferences for text-to-image generation

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.148996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9ea3eedc-4829-42eb-af89-dd1f23372705 · outbound

This paper cites Multi-concept customization of text-to-image diffusion.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Multi-concept customization of text-to-image diffusion

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.133601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 171c281f-5efc-462a-8ca5-7e4cbdd4b9cc · outbound

This paper cites AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.326328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d53351-3fc1-47f8-8915-6b9682c2b3c1 · outbound

This paper cites Playground v2.5: Three in- sights towards enhancing aesthetic quality in text-to-image generation, 2024.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Playground v2.5: Three in- sights towards enhancing aesthetic quality in text-to-image generation, 2024

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.118411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation da05146a-8064-4abf-9c5e-c6131491e166 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for uni- fied vision-language understanding and generation.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Blip: Bootstrapping language-image pre-training for uni- fied vision-language understanding and generation

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.103386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 904e80b3-4654-404e-8d95-293f16e3e292 · outbound

This paper cites Learning warped guidance for blind face restoration.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Learning warped guidance for blind face restoration

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.088744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 29e06a82-962a-450d-a100-f919021289f2 · outbound

This paper cites Enhanced blind face restoration with multi-exemplar images and adaptive spatial feature fusion.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Enhanced blind face restoration with multi-exemplar images and adaptive spatial feature fusion

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.073289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1f76afff-8075-4ccc-bba0-ed2d66ab3299 · outbound

This paper cites Learning dual memory dic- tionaries for blind face restoration.IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Learning dual memory dic- tionaries for blind face restoration.IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.056550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c62b50b8-e0ee-4cfe-a1e4-86293ca17358 · outbound

This paper cites PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.355450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbb84cfd-0e08-491d-b4e3-b9c6eb9be24d · outbound

This paper cites Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.360430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e77acbb4-375d-4d97-a053-ace6682d59c9 · outbound

This paper cites Rich human feedback for text-to-image generation.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Rich human feedback for text-to-image generation

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.040248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f7985be2-099e-41ac-b15c-69375fc1fb51 · outbound

This paper cites Multi-branch face quality assess- ment for face recognition.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Multi-branch face quality assess- ment for face recognition

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.023241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c2d3026f-a922-463e-8e7a-d1730cc15240 · outbound

This paper cites Microsoft coco: Common objects in context.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Microsoft coco: Common objects in context

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:11.008040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b0f7b278-3ef2-4f80-a4cf-994cadb217f2 · outbound

This paper cites DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.379022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ba76694-cbe8-45d0-b8a1-65ad87f314e2 · outbound

This paper cites Visual instruction tuning.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Visual instruction tuning

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.992201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5fb7f03f-f539-49df-be64-b1f1a5de6f05 · outbound

This paper cites Blind quality assessment based on pseudo-reference image.IEEE Transactions on Multimedia (TMM), 20(8):2049–2062, 2018.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Blind quality assessment based on pseudo-reference image.IEEE Transactions on Multimedia (TMM), 20(8):2049–2062, 2018

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.976178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 05ee05b2-f3f8-4538-aba8-85685c0bae48 · outbound

This paper cites Blind image quality estimation via distortion aggravation.IEEE Transactions on Broadcasting, 64(2): 508–517, 2018.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Blind image quality estimation via distortion aggravation.IEEE Transactions on Broadcasting, 64(2): 508–517, 2018

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.958111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e496d7ac-65e4-4d7e-b1ed-87ea68cab0af · outbound

This paper cites Perceptual video quality assessment: A survey.Science China Information Sciences, 67(11): 211301, 2024.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Perceptual video quality assessment: A survey.Science China Information Sciences, 67(11): 211301, 2024

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.942036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8fa0ef26-b8dc-4bde-8d73-32d14d506a2b · outbound

This paper cites completely blind.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration completely blind

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.926036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3f150026-b016-4346-9169-01eb48018e9d · outbound

This paper cites Agedb: the first manually collected, in-the-wild age database.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Agedb: the first manually collected, in-the-wild age database

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.910619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a5c7c3aa-ab98-4628-9989-88672910132d · outbound

This paper cites Sdd-fiqa: Unsupervised face image quality assess- ment with similarity distribution distance.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Sdd-fiqa: Unsupervised face image quality assess- ment with similarity distribution distance

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.894286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5dc5d659-b074-4d50-b477-a71a5578b50e · outbound

This paper cites Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.416801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5eff706-fcc0-4971-98d5-96b679583d4e · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.421652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ba476b-3721-4e51-a78d-973ff897679a · outbound

This paper cites Zero-shot text-to-image generation, 2021.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Zero-shot text-to-image generation, 2021

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.426584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 430798b7-59a4-41f3-a2a1-7130a6ad91ce · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.431321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b219e2a-d6bb-43f2-912f-2aac25e6c5fd · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration High-resolution image synthesis with latent diffusion models

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.868274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 10a8ebb6-1c63-408e-ae41-f0d1efc0ae37 · outbound

This paper cites Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.853227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 17eac0fe-1216-400b-b494-f066942df403 · outbound

This paper cites Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.837296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8043c049-3521-4c8f-8d34-71d3832c1b75 · outbound

This paper cites an unresolved cited work.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-11T13:28:10.821478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 97d11490-da67-45ec-a919-a8c511bf78c1 · outbound

This paper cites Methodology for the subjective assessment of the quality of television pictures.Recommendation ITU-R BT, 500(13), 2012.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Methodology for the subjective assessment of the quality of television pictures.Recommendation ITU-R BT, 500(13), 2012

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.807374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a6904c97-8a60-4420-a220-32bbd693ab35 · outbound

This paper cites Photo uncrop.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Photo uncrop

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.792593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1b25537d-cc10-4411-81ff-7d3383eaac75 · outbound

This paper cites Responsible re- search with crowds: pay crowdworkers at least minimum wage.Communications of the ACM, 61(3):39–41, 2018.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Responsible re- search with crowds: pay crowdworkers at least minimum wage.Communications of the ACM, 61(3):39–41, 2018

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.778021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 03e9a3e7-41f5-407d-a2ef-363325f98b4c · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.468897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89abb9ad-b564-4d6c-8cbf-8c4d9f17ba3c · outbound

This paper cites Denoising Diffusion Implicit Models.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Denoising Diffusion Implicit Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.473947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63564549-019d-4c0f-b732-75ebf3a0f87e · outbound

This paper cites Blindly assess image qual- ity in the wild guided by a self-adaptive hyper network.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Blindly assess image qual- ity in the wild guided by a self-adaptive hyper network

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.763114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b8e09704-cafb-48c3-a194-12daec45bb1c · outbound

This paper cites Going the extra mile in face image quality assess- ment: A novel database and model.IEEE Transactions on Multimedia, 2023.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Going the extra mile in face image quality assess- ment: A novel database and model.IEEE Transactions on Multimedia, 2023

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.748106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 27856703-bcc6-48d4-8e9f-bbf4787d07ef · outbound

This paper cites Ser-fiq: Unsupervised estimation of face image quality based on stochastic embed- ding robustness.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Ser-fiq: Unsupervised estimation of face image quality based on stochastic embed- ding robustness

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.733770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b0480844-51a8-417c-a3b3-91a9262310b5 · outbound

This paper cites Towards all-in-one medical image re-identification.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Towards all-in-one medical image re-identification

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.719244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9a429446-321c-4795-8103-08a3df7947f1 · outbound

This paper cites Stylegan2 distillation for feed-forward image manipulation.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Stylegan2 distillation for feed-forward image manipulation

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.704648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1db0fb2a-5463-4095-9e15-0c525effa9b5 · outbound

This paper cites Aigciqa2023: A large-scale im- age quality assessment database for ai generated images: from the perspectives of quality, authenticity and corre- spondence.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Aigciqa2023: A large-scale im- age quality assessment database for ai generated images: from the perspectives of quality, authenticity and corre- spondence

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.690350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6a6d2ec4-ec1c-4725-b63b-969c7bad0bec · outbound

This paper cites Aigciqa2023: A large-scale im- age quality assessment database for ai generated images: from the perspectives of quality, authenticity and corre- spondence.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Aigciqa2023: A large-scale im- age quality assessment database for ai generated images: from the perspectives of quality, authenticity and corre- spondence

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.675866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca570237-a40b-418a-ab7c-5d309b683ab0 · outbound

This paper cites Exploiting Diffusion Prior for Real-World Image Super-Resolution.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Exploiting Diffusion Prior for Real-World Image Super-Resolution

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.511223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1693e052-5e6c-4277-b79c-a00331e13b7a · outbound

This paper cites Quality Assessment for AI Generated Images with Instruction Tuning.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Quality Assessment for AI Generated Images with Instruction Tuning

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.516085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec95d0f6-8897-455e-bf65-aaa801fb1f97 · outbound

This paper cites Chan, and Chen Change Loy.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Chan, and Chen Change Loy

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.660440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2499f1e3-77a4-44d5-a7fe-3292e6a04245 · outbound

This paper cites Xintao Wang, Honglun Zhang, Chao Dong, and Ying Shan.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Xintao Wang, Honglun Zhang, Chao Dong, and Ying Shan

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.645998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 74eb4c1a-26fa-4bce-8e42-472a7469a856 · outbound

This paper cites InstantID: Zero-shot Identity-Preserving Generation in Seconds.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration InstantID: Zero-shot Identity-Preserving Generation in Seconds

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.530098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4b8864-95f0-4fbd-9571-81b248ee9d98 · outbound

This paper cites A survey of deep face restoration: Denoise, super-resolution, deblur, artifact re- moval.arXiv preprint arXiv:2211.02831, 2022.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration A survey of deep face restoration: Denoise, super-resolution, deblur, artifact re- moval.arXiv preprint arXiv:2211.02831, 2022

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-11T13:28:09.535100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea9e9d8-5210-480f-99d1-72a8fcf62338 · outbound

This paper cites Real-esrgan: Training real-world blind super-resolution with pure synthetic data.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Real-esrgan: Training real-world blind super-resolution with pure synthetic data

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.632037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6ea9ac46-4b48-4f52-b74b-87ab8685b886 · outbound

This paper cites To- wards real-world blind face restoration with generative fa- cial prior.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration To- wards real-world blind face restoration with generative fa- cial prior

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.617145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5fae0384-2418-4eff-99c2-fe94ec794551 · outbound

This paper cites To- wards real-world blind face restoration with generative fa- cial prior.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration To- wards real-world blind face restoration with generative fa- cial prior

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.602051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a76a67ef-d970-46fe-826f-a93172ae61a9 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.IEEE Transactions on Image Pro- cessing (TIP), 13(4):600–612, 2004.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Image quality assessment: from error visibility to structural similarity.IEEE Transactions on Image Pro- cessing (TIP), 13(4):600–612, 2004

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.586803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 35a27293-0041-47f0-a6a4-601dea5f851c · outbound

This paper cites Dr2: Diffusion-based robust degradation remover for blind face restoration.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Dr2: Diffusion-based robust degradation remover for blind face restoration

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.572380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 91221b86-57f7-42ba-a94e-2695d509b31c · outbound

This paper cites Elite: Encoding visual con- cepts into textual embeddings for customized text-to-image generation.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Elite: Encoding visual con- cepts into textual embeddings for customized text-to-image generation

Reference 101

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:28:10.557602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers