arxiv: 2603.22607 · v2 · submitted 2026-03-23 · 💻 cs.CV

Recognition: no theorem link

Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off

Fulvio Sanguigni , Davide Lobba , Bin Ren , Marcella Cornia , Nicu Sebe , Rita Cucchiara

Authors on Pith no claims yet

Pith reviewed 2026-05-15 00:09 UTC · model grok-4.3

classification 💻 cs.CV

keywords virtual try-onvirtual try-offgarment editingtext-guided editingdiffusion modelsfashion datasetmultimodal pipelineinstruction following

0 comments

The pith

Dress-ED provides the first large-scale benchmark unifying virtual try-on, virtual try-off and text-guided garment editing.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces Dress-ED as a new benchmark that brings virtual try-on, virtual try-off and instruction-based garment editing into one dataset. Each entry supplies an in-shop garment image, the person wearing that garment, edited versions of both, and a natural-language instruction describing the desired change. This structure supports controllable modifications such as altering color, pattern or sleeve length within a single framework. The data is produced by an automated pipeline that uses multimodal models to understand garments, diffusion models to perform edits and language models to verify quality, yielding more than 146,000 samples across three garment categories and seven edit types. A baseline multimodal diffusion model is also presented that processes both the text instruction and visual cues to execute the edits.

Core claim

We introduce the Dress Editing Dataset (Dress-ED), the first large-scale benchmark that unifies VTON, VTOFF, and text-guided garment editing within a single framework. Each sample in Dress-ED includes an in-shop garment image, the corresponding person image wearing the garment, their edited counterparts, and a natural-language instruction of the desired modification. Built through a fully automated multimodal pipeline that integrates MLLM-based garment understanding, diffusion-based editing, and LLM-guided verification, Dress-ED comprises over 146k verified quadruplets spanning three garment categories and seven edit types, including both appearance (e.g., color, pattern, material) and the e

What carries the argument

The quadruplet consisting of in-shop garment image, person image, edited counterparts and natural-language instruction, generated by an automated pipeline of MLLM understanding, diffusion editing and LLM verification.

If this is right

Models trained on the dataset can perform text-guided virtual try-on and virtual try-off in one system.
The benchmark supports both appearance edits such as color and pattern changes and structural edits such as sleeve length and neckline adjustments.
A single evaluation set now exists for instruction-driven fashion synthesis tasks that were previously handled separately.
The proposed multimodal diffusion baseline shows how linguistic instructions and visual garment cues can be jointly processed.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Interactive e-commerce tools could let users describe garment changes in plain language and see results immediately.
Training on this dataset may improve a model's ability to handle unseen edit instructions if the automated creation process scales cleanly.
Adding real-world user instructions as a test set would check whether models generalize beyond the generated data.

Load-bearing premise

The fully automated multimodal pipeline integrating MLLM-based garment understanding, diffusion-based editing, and LLM-guided verification produces accurate, high-quality data without significant artifacts or verification errors.

What would settle it

A random sample of the released quadruplets in which the edited images fail to match the supplied instructions or contain visible artifacts would falsify the benchmark's claimed reliability.

Figures

Figures reproduced from arXiv: 2603.22607 by Bin Ren, Davide Lobba, Fulvio Sanguigni, Marcella Cornia, Nicu Sebe, Rita Cucchiara.

**Figure 1.** Figure 1: We propose the Dress Editing Dataset (Dress-ED), the first benchmark for instruction-driven virtual try-on and try-off with over 146k verified samples across seven editing types, including both appearance and structural modifications. Abstract. Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruction. However, ex… view at source ↗

**Figure 2.** Figure 2: Overview of the Dress-ED curation pipeline. [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗

**Figure 3.** Figure 3: Overview of the proposed Dress-EM architecture for instruction-driven fashion editing. (DiT) into a cohesive architecture, as illustrated in [PITH_FULL_IMAGE:figures/full_fig_p010_3.png] view at source ↗

**Figure 4.** Figure 4: Qualitative results for edited VTON unpaired setting (first two rows) and edited VTOFF (last two rows), showing realistic and instruction-consistent edits. pose, and garment details, further confirming the effectiveness of the proposed approach. 6 Conclusion We introduced Dress-ED, the first large-scale dataset and benchmark for instruction-driven fashion editing that unifies VTON, VTOFF, and text-guided g… view at source ↗

**Figure 5.** Figure 5: Sample of label maps, masks, in-shop garment and FitDiT result. FitDiT uses bounding boxes as input masks. These bounding boxes are extracted from the label maps of a clothed person extracted using a parser. A visual example is provided in [PITH_FULL_IMAGE:figures/full_fig_p019_5.png] view at source ↗

**Figure 6.** Figure 6: Samples from Dress-ED across the different edit types, including the original person-garment pair, the corresponding edited outputs, and the textual instruction. Addable Details (category-specific) – Upper-body: bow (neck), pockets, chest pocket, zipper, buttons. – Lower-body: belt, drawstring. – Dresses: belt, fitted belt, pockets, drawstring, bow (neck/waist). Removable/Colorable/Replaceable Details: sam… view at source ↗

**Figure 7.** Figure 7: Editing instruction taxonomy showing the distribution of edit types in Dress-ED, covering both appearance-level changes (e.g., color, pattern, material) and structural modifications (e.g., sleeve length, neckline, shape). ditional examples from Dress-ED are provided in [PITH_FULL_IMAGE:figures/full_fig_p022_7.png] view at source ↗

**Figure 8.** Figure 8: Qualitative results for edited VTON (left, unpaired setting) and VTOFF (right), showing realistic and instruction-consistent edits. D Additional Discussion and Clarifications This section provides further explanations on several components of our pipeline. We outline the motivations behind key design choices, describe their practical implications, and discuss limitations relevant to interpreting the datase… view at source ↗

**Figure 9.** Figure 9: User study interface. suring whether models follow the intended transformation, while remaining compatible with future real-world data collection or domain adaptation. In this sense, the dataset serves as a structured foundation on top of which broader and more diverse fashion-editing scenarios can be explored. D.2 LLM-as-Judge and Evaluation Consistency GPT-5 [40] is employed solely as a non-generative ev… view at source ↗

**Figure 10.** Figure 10: Confusion matrix of our user study. To enable reproducible large-scale verification, we distill GPT-5’s judgments into a smaller open-source MLLM (InternVL-3.5 [53]). Although this introduces some dependence between data construction and evaluation, our final benchmark reports model-agnostic evaluation metrics (i.e., including DINO and standard perceptual scores) which remain independent of both GPT-5… view at source ↗

**Figure 9.** Figure 9: Participants were tasked with assessing the edit correctness of triplets [PITH_FULL_IMAGE:figures/full_fig_p025_9.png] view at source ↗

read the original abstract

Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruction. However, existing datasets remain static, lacking instruction-driven editing for controllable and interactive fashion generation. In this work, we introduce the Dress Editing Dataset (Dress-ED), the first large-scale benchmark that unifies VTON, VTOFF, and text-guided garment editing within a single framework. Each sample in Dress-ED includes an in-shop garment image, the corresponding person image wearing the garment, their edited counterparts, and a natural-language instruction of the desired modification. Built through a fully automated multimodal pipeline that integrates MLLM-based garment understanding, diffusion-based editing, and LLM-guided verification, Dress-ED comprises over 146k verified quadruplets spanning three garment categories and seven edit types, including both appearance (e.g., color, pattern, material) and structural (e.g., sleeve length, neckline) modifications. Based on this benchmark, we further propose a unified multimodal diffusion framework that jointly reasons over linguistic instructions and visual garment cues, serving as a strong baseline for instruction-driven VTON and VTOFF. Dataset and code will be made publicly available. Project page: https://furio1999.github.io/Dress-ED/

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

Dress-ED gives a new unified dataset for text-guided VTON and VTOFF edits at 146k scale, but its automated verification step lacks any reported human error checks.

read the letter

The main takeaway is that this paper ships Dress-ED, a dataset of over 146k quadruplets that puts virtual try-on, virtual try-off, and text-driven garment edits into one collection. Each sample pairs an in-shop garment, a person wearing it, an edited version, and a natural-language instruction covering changes like color, pattern, material, sleeve length, or neckline. They also train a baseline multimodal diffusion model that conditions on both the text and the visual garment cues. The dataset spans three garment categories and seven edit types, which is broader than the static collections that came before. Releasing the data and code publicly is the practical step that matters most here. The automated pipeline that combines MLLM garment parsing, diffusion editing, and LLM verification is a reasonable way to reach that scale without manual labeling at every step. The soft spot is exactly the one the stress-test note flags: the claim that the quadruplets are verified rests entirely on the LLM verification stage, with no quantitative human agreement rates or sampled error analysis provided in the abstract. Without those numbers it is hard to judge how many artifacts or instruction mismatches made it through. This work is aimed at researchers building controllable generative models for fashion images or e-commerce tools. If the full paper adds even modest human validation on a subset, the benchmark could become a standard testbed. I would send it to peer review. The dataset idea is concrete enough to justify referee time, and the authors can strengthen the quality evidence during revision.

Referee Report

1 major / 1 minor

Summary. The paper introduces the Dress Editing Dataset (Dress-ED), the first large-scale benchmark unifying VTON, VTOFF, and text-guided garment editing. Each of the >146k samples consists of an in-shop garment image, corresponding person image, edited counterparts, and a natural-language instruction. The dataset is built via a fully automated multimodal pipeline (MLLM garment understanding + diffusion editing + LLM-guided verification) spanning three garment categories and seven edit types (appearance and structural). A unified multimodal diffusion framework is proposed as a baseline for instruction-driven tasks.

Significance. If the automated pipeline produces high-quality, accurately labeled quadruplets at this scale, Dress-ED would provide the first unified benchmark for controllable, instruction-driven virtual try-on and try-off, enabling progress on interactive multimodal fashion synthesis models.

major comments (1)

[Abstract and Dataset Construction] Abstract and Dataset Construction: the claim that the 146k quadruplets are 'verified' and high-quality rests entirely on the LLM-guided verification step correctly rejecting low-fidelity edits and instruction mismatches. No quantitative human evaluation (agreement rates, error rates on a sampled subset, or false-positive acceptance of artifacts) is reported to bound the reliability of this automated verification.

minor comments (1)

[Abstract] The abstract states that dataset and code will be made publicly available but provides no details on release timeline, repository, or licensing.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. We agree that quantitative human validation would strengthen the claims about dataset quality and will incorporate the requested evaluation in the revision.

read point-by-point responses

Referee: [Abstract and Dataset Construction] Abstract and Dataset Construction: the claim that the 146k quadruplets are 'verified' and high-quality rests entirely on the LLM-guided verification step correctly rejecting low-fidelity edits and instruction mismatches. No quantitative human evaluation (agreement rates, error rates on a sampled subset, or false-positive acceptance of artifacts) is reported to bound the reliability of this automated verification.

Authors: We agree that the absence of quantitative human evaluation leaves the reliability of the LLM-guided verification step insufficiently bounded. In the revised manuscript we will add a dedicated subsection under Dataset Construction that reports a human study on a randomly sampled subset of 1,000 quadruplets. The study will include: (i) agreement rate between the LLM verifier and three independent human annotators, (ii) false-positive rate (human-accepted artifacts that the LLM incorrectly passed), and (iii) error rates stratified by edit type. We will also release the annotation protocol and sampled subset to allow reproducibility. This addition directly addresses the concern and provides empirical bounds on the automated pipeline's quality. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper's contribution is empirical: it describes construction of the Dress-ED dataset via an automated pipeline (MLLM garment understanding + diffusion editing + LLM verification) and trains a baseline multimodal diffusion model. No mathematical derivations, equations, fitted parameters, or predictions appear in the provided text. The central claims rest on the pipeline's output of 146k quadruplets rather than any self-referential reduction, self-citation load-bearing premise, or renaming of known results. Any self-citations present are incidental and not required to justify the dataset's existence or the baseline's architecture by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper's primary addition is the curated dataset and baseline rather than new theoretical constructs or parameters.

axioms (1)

domain assumption Pre-trained multimodal LLMs and diffusion models can reliably understand garments and generate accurate edits for verification
The automated pipeline depends on these existing models for data generation and quality checks.

pith-pipeline@v0.9.0 · 5547 in / 1159 out tokens · 56988 ms · 2026-05-15T00:09:51.975862+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

72 extracted references · 12 canonical work pages · 7 internal anchors

[1]

AI, F.: Fashn human parser: Segformer for fashion human parsing (2024)

2024
[2]

In: CVPR (2025)

Avrahami, O., Patashnik, O., Fried, O., Nemchinov, E., Aberman, K., Lischinski, D., Cohen-Or, D.: Stable Flow: Vital Layers for Training-Free Image Editing. In: CVPR (2025)

2025
[3]

Qwen3-VL Technical Report

Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[4]

In: ECCV (2022)

Bai, S., Zhou, H., Li, Z., Zhou, C., Yang, H.: Single Stage Virtual Try-On Via Deformable Attention Flows. In: ECCV (2022)

2022
[5]

In: ICCV (2023)

Baldrati, A., Morelli, D., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing. In: ICCV (2023)

2023
[6]

Demystifying MMD GANs

Bińkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. arXiv preprint arXiv:1801.01401 (2018)

work page internal anchor Pith review arXiv 2018
[7]

In: CVPR (2023)

Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: Learning to follow image editing instructions. In: CVPR (2023)

2023
[8]

In: ICCV (2023)

Chen, C.Y., Chen, Y.C., Shuai, H.H., Cheng, W.H.: Size Does Matter: Size-aware Virtual Try-on via Clothing-oriented Transformation Try-on Network. In: ICCV (2023)

2023
[9]

In: CVPR (2021)

Choi, S., Park, S., Lee, M., Choo, J.: VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization. In: CVPR (2021)

2021
[10]

In: ICLR (2025)

Chong, Z., Dong, X., Li, H., Zhang, S., Zhang, W., Zhang, X., Zhao, H., Jiang, D., Liang, X.: CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models. In: ICLR (2025)

2025
[11]

In: WACV (2024)

Cui, A., Mahajan, J., Shah, V., Gomathinayagam, P., Liu, C., Lazebnik, S.: Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images. In: WACV (2024)

2024
[12]

In: ICCV (2021)

Cui, A., McKee, D., Lazebnik, S.: Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-On and Outfit Editing. In: ICCV (2021)

2021
[13]

IEEE Trans

Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Image Quality Assessment: Unifying Structure and Texture Similarity. IEEE Trans. PAMI44(5), 2567–2581 (2020)

2020
[14]

In: ICML (2024)

Esser, P., Kulal, S., Blattmann, A., Entezari, R., Müller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F., et al.: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In: ICML (2024)

2024
[15]

In: WACV (2022)

Fele, B., Lampe, A., Peer, P., Struc, V.: C-VTON: Context-Driven Image-Based Virtual Try-On Network. In: WACV (2022)

2022
[16]

In: ICLR (2024)

Fu, T.J., Hu, W., Du, X., Wang, W.Y., Yang, Y., Gan, Z.: Guiding Instruction-based Image Editing via Multimodal Large Language Models. In: ICLR (2024)

2024
[17]

In: ECCV (2024)

Garibi, D., Patashnik, O., Voynov, A., Averbuch-Elor, H., Cohen-Or, D.: ReNoise: Real Image Inversion Through Iterative Noising. In: ECCV (2024)

2024
[18]

In: CVPR (2019) 16 F

Ge, Y., Zhang, R., Wang, X., Tang, X., Luo, P.: DeepFashion2: A Versatile Bench- mark for Detection, Pose Estimation, Segmentation and Re-Identification of Cloth- ing Images. In: CVPR (2019) 16 F. Sanguigni, et al

2019
[19]

In: ICCV (2025)

Girella, F., Talon, D., Liu, Z., Ruan, Z., Wang, Y., Cristani, M.: LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing. In: ICCV (2025)

2025
[20]

In: ICCV (2025)

Guo, H., Zeng, B., Song, Y., Zhang, W., Zhang, C., Liu, J.: Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks. In: ICCV (2025)

2025
[21]

In: CVPR (2018)

Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S.: VITON: An Image-Based Virtual Try-On Network. In: CVPR (2018)

2018
[22]

In: ICLR (2022)

Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al.: LoRA: Low-Rank Adaptation of Large Language Models. In: ICLR (2022)

2022
[23]

In: CVPR (2025)

Huang, S., Li, H., Zheng, C., Ge, M., Gao, W., Wang, L., Liu, L.: Text-Driven Fashion Image Editing with Compositional Concept Learning and Counterfactual Abduction. In: CVPR (2025)

2025
[24]

In: ICLR (2025)

Hui, M., Yang, S., Zhao, B., Shi, Y., Wang, H., Wang, P., Zhou, Y., Xie, C.: HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing. In: ICLR (2025)

2025
[25]

In: CVPR (2025)

Jiang, B., Hu, X., Luo, D., He, Q., Xu, C., Peng, J., Zhang, J., Wang, C., Wu, Y., Fu, Y.: FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on. In: CVPR (2025)

2025
[26]

arXiv preprint arXiv:2504.13109 (2025)

Jiao, G., Huang, B., Wang, K.C., Liao, R.: UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models. arXiv preprint arXiv:2504.13109 (2025)

work page arXiv 2025
[27]

In: ECCV (2024)

Khirodkar, R., Bagautdinov, T., Martinez, J., Zhaoen, S., James, A., Selednik, P., Anderson, S., Saito, S.: Sapiens: Foundation for human vision models. In: ECCV (2024)

2024
[28]

In: CVPR (2024)

Kim, J., Gu, G., Park, M., Park, S., Choo, J.: StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On. In: CVPR (2024)

2024
[29]

Labs, B.F.: FLUX.2: Frontier Visual Intelligence.https://bfl.ai/blog/flux-2 (2025)

2025
[30]

arXiv preprint arXiv:2508.04825 (2025)

Lee, S., Kwak, J.g.: Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off. arXiv preprint arXiv:2508.04825 (2025)

work page arXiv 2025
[31]

arXiv preprint arXiv:2306.02928 (2023)

Lepage, S., Mary, J., Picard, D.: LRVS-Fashion: Extending Visual Search with Referring Instructions. arXiv preprint arXiv:2306.02928 (2023)

work page arXiv 2023
[32]

In: CVPR Workshops (2025)

Li, Q., Qiu, S., Han, J., Xu, X., Seyfioglu, M.S., Koo, K.K., Bouyarmane, K.: DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing. In: CVPR Workshops (2025)

2025
[33]

In: NeurIPS (2024)

Li, Y., Zhou, H., Shang, W., Lin, R., Chen, X., Ni, B.: Anyfit: Controllable virtual try-on for any combination of attire across any scenario. In: NeurIPS (2024)

2024
[34]

One Model for All: Unified Try-On and Try-Off in Any Pose via LLM-Inspired Bidirectional Tweedie Diffusion

Liu, J., He, Z., Wang, G., Li, G., Lin, L.: One Model For All: Partial Diffusion for Unified Try-On and Try-Off in Any Pose. arXiv preprint arXiv:2508.04559 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[35]

Step1X-Edit: A Practical Framework for General Image Editing

Liu, S., Han, Y., Xing, P., Yin, F., Wang, R., Cheng, W., Liao, J., Wang, Y., Fu, H., Han, C., Li, G., Peng, Y., Sun, Q., Wu, J., Cai, Y., Ge, Z., Ming, R., Xia, L., Zeng, X., Zhu, Y., Jiao, B., Zhang, X., Yu, G., Jiang, D.: Step1x-edit: A practical framework for general image editing. arXiv preprint arXiv:2504.17761 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[36]

In: ICLR (2026)

Lobba, D., Sanguigni, F., Ren, B., Cornia, M., Cucchiara, R., Sebe, N.: Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals. In: ICLR (2026)

2026
[37]

In: ICLR (2019)

Loshchilov, I., Hutter, F.: Decoupled Weight Decay Regularization. In: ICLR (2019)

2019
[38]

In: ACM Multimedia (2023) Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off 17

Morelli, D., Baldrati, A., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On. In: ACM Multimedia (2023) Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off 17

2023
[39]

In: ECCV (2022)

Morelli, D., Matteo, F., Marcella, C., Federico, L., Fabio, C., Rita, C.: Dress Code: High-Resolution Multi-Category Virtual Try-On. In: ECCV (2022)

2022
[40]

OpenAI: Introducing GPT-5 (2025)

2025
[41]

DINOv2: Learning Robust Visual Features without Supervision

Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et al.: DINOv2: Learning Robust Visual Features without Supervision. arXiv preprint arXiv:2304.07193 (2023)

work page internal anchor Pith review Pith/arXiv arXiv 2023
[42]

In: CVPR (2022)

Parmar, G., Zhang, R., Zhu, J.Y.: On Aliased Resizing and Surprising Subtleties in GAN Evaluation. In: CVPR (2022)

2022
[43]

In: ICCV (2025)

Patel, M., Wen, S., Metaxas, D.N., Yang, Y.: Steering Rectified Flow Models in the Vector Field for Controlled Image Generation. In: ICCV (2025)

2025
[44]

In: ICCV (2025)

Pathiraja, B., Patel, M., Singh, S., Yang, Y., Baral, C.: Refedit: A benchmark and method for improving instruction-based image editing model on referring expressions. In: ICCV (2025)

2025
[45]

In: ICCV (2023)

Peebles, W., Xie, S.: Scalable Diffusion Models with Transformers. In: ICCV (2023)

2023
[46]

In: SC (2021)

Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: ZeRO: Memory Optimizations Toward Training Trillion Parameter Models. In: SC (2021)

2021
[47]

ACM TOMM20(4), 1–20 (2023)

Ren, B., Tang, H., Meng, F., Runwei, D., Torr, P.H., Sebe, N.: Cloth Interactive Transformer for Virtual Try-On. ACM TOMM20(4), 1–20 (2023)

2023
[48]

In: ICLR (2025)

Rout, L., Chen, Y., Ruiz, N., Caramanis, C., Shakkottai, S., Chu, W.S.: Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations. In: ICLR (2025)

2025
[49]

In: CVPR (2025)

Sheynin, S., Polyak, A., Singer, U., Kirstain, Y., Zohar, A., Ashual, O., Parikh, D., Taigman, Y.: Emu edit: Precise image editing via recognition and generation tasks. In: CVPR (2025)

2025
[50]

In: BMVC (2024)

Velioglu, R., Bevandic, P., Chan, R., Hammer, B.: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models. In: BMVC (2024)

2024
[51]

In: ICCV Workshops (2025)

Velioglu, R., Bevandic, P., Chan, R., Hammer, B.: MGT: Extending Virtual Try-Off to Multi-Garment Scenarios. In: ICCV Workshops (2025)

2025
[52]

In: ECCV (2018)

Wang, B., Zheng, H., Liang, X., Chen, Y., Lin, L., Yang, M.: Toward Characteristic- Preserving Image-based Virtual Try-On Network. In: ECCV (2018)

2018
[53]

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Wang, W., Gao, Z., Gu, L., Pu, H., Cui, L., Wei, X., Liu, Z., Jing, L., Ye, S., Shao, J., et al.: InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency. arXiv preprint arXiv:2508.18265 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[54]

IEEE Trans

Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Processing13(4), 600–612 (2004)

2004
[55]

In: ICLR (2025)

Wei, C., Xiong, Z., Ren, W., Du, X., Zhang, G., Chen, W.: OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision. In: ICLR (2025)

2025
[56]

Qwen-Image Technical Report

Wu, C., Li, J., Zhou, J., Lin, J., Gao, K., Yan, K., Yin, S.m., Bai, S., Xu, X., Chen, Y., et al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[57]

arXiv preprint arXiv:2412.08573 (2024)

Xarchakos, I., Koukopoulos, T.: TryOffAnyone: Tiled Cloth Generation from a Dressed Person. arXiv preprint arXiv:2412.08573 (2024)

work page arXiv 2024
[58]

In: CVPR (2023)

Xie, Z., Huang, Z., Dong, X., Zhao, F., Dong, H., Zhang, X., Zhu, F., Liang, X.: GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning. In: CVPR (2023)

2023
[59]

In: AAAI (2024)

Xie, Z., Li, H., Ding, H., Li, M., Cao, Y.: HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models. In: AAAI (2024)

2024
[60]

In: CVPR (2023) 18 F

Yan, K., Gao, T., Zhang, H., Xie, C.: Linking garment with person via semantically associated landmarks for virtual try-on. In: CVPR (2023) 18 F. Sanguigni, et al

2023
[61]

In: ACM Multimedia (2024)

Yang,L.,Zeng,B.,Liu,J.,Li,H.,Xu,M.,Zhang,W.,Yan,S.:EditWorld:Simulating World Dynamics for Instruction-Following Image Editing. In: ACM Multimedia (2024)

2024
[62]

arXiv preprint arXiv:2504.13143 (2025)

Yang, S., Hui, M., Zhao, B., Zhou, Y., Ruiz, N., Xie, C.: Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark. arXiv preprint arXiv:2504.13143 (2025)

work page arXiv 2025
[63]

In: NeurIPS (2025)

Ye, Y., He, X., Li, Z., Lin, B., Yuan, S., Yan, Z., Hou, B., Yuan, L.: Imgedit: A unified image editing dataset and benchmark. In: NeurIPS (2025)

2025
[64]

In: ACM Multimedia (2025)

Yin, D., Guo, J., Lu, H., Wu, F., Lu, D.: EditGarment: An Instruction-Based Garment Editing Dataset Constructed with Automated MLLM Synthesis and Semantic-Aware Evaluation. In: ACM Multimedia (2025)

2025
[65]

In: CVPR (2025)

Yu, Q., Chow, W., Yue, Z., Pan, K., Wu, Y., Wan, X., Li, J., Tang, S., Zhang, H., Zhuang, Y.: Anyedit: Mastering unified high-quality image editing for any idea. In: CVPR (2025)

2025
[66]

In: NeurIPS (2023)

Zhang, K., Mo, L., Chen, W., Sun, H., Su, Y.: Magicbrush: A manually annotated dataset for instruction-guided image editing. In: NeurIPS (2023)

2023
[67]

In: CVPR (2018)

Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)

2018
[68]

In: CVPR (2024)

Zhang, S., Yang, X., Feng, Y., Qin, C., Chen, C.C., Yu, N., Chen, Z., Wang, H., Savarese, S., Ermon, S., et al.: HIVE: Harnessing Human Feedback for Instructional Visual Editing. In: CVPR (2024)

2024
[69]

In: NeurIPS (2024)

Zhao, H., Ma, X.S., Chen, L., Si, S., Wu, R., An, K., Yu, P., Zhang, M., Li, Q., Chang, B.: Ultraedit: Instruction-based fine-grained image editing at scale. In: NeurIPS (2024)

2024
[70]

In: CVPR (2025)

Zhou, Z., Liu, S., Han, X., Liu, H., Ng, K.W., Xie, T., Cong, Y., Li, H., Xu, M., Pérez-Rúa, J.M., Patel, A., Xiang, T., Shi, M., He, S.: Learning Flow Fields in Attention for Controllable Person Image Generation. In: CVPR (2025)

2025
[71]

In: CVPR (2024)

Zhu, L., Li, Y., Liu, N., Peng, H., Yang, D., Kemelmacher-Shlizerman, I.: M&m vto: Multi-garment virtual try-on and editing. In: CVPR (2024)

2024
[72]

Change the color of the garment to[Target Color]

Zhu, L., Yang, D., Zhu, T., Reda, F., Chan, W., Saharia, C., Norouzi, M., Kemelmacher-Shlizerman, I.: TryOnDiffusion: A Tale of Two UNets. In: CVPR (2023) Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off 19 A Additional Implementation Details Training Configuration.During training, we employ DeepSpeed [46] for mem- ory optimization and ...

2023