pith. sign in

arxiv: 2606.27584 · v1 · pith:LJOAZAHOnew · submitted 2026-06-25 · 💻 cs.CV · cs.AI

CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance

Hana Kim , Minje Kim , Tae-Kyun Kim This is my paper

Pith reviewed 2026-06-29 01:23 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords 3D inpaintingGaussian Splatting2D-3D consistencyobject insertiondiffusion modelsscene editingmulti-view consistency
0
0 comments X

The pith

CoIn connects 2D diffusion inpainting to 3D Gaussian Splatting through a bidirectional multi-stage pipeline to handle both object removal and insertion with flexible masks.

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

The paper introduces CoIn to solve 3D scene inpainting by linking 2D models with 3D representations. It starts with diffusion-based inpainting on arbitrary masks, then builds a coarse 3D scene using Reference Adaptive GS, warps features back for consistency, and refines with a discriminator. This bidirectional flow aims to achieve multi-view consistency without needing precise multi-view masks. A sympathetic reader would care because it expands 3D editing beyond removal-only tasks to include insertions in scenes with limited views.

Core claim

CoIn is a framework that first uses a 2D diffusion model to generate inpainted images with flexible masks, then employs Reference Adaptive GS with Feature Attention to reconstruct a coarse 3D scene, provides geometric guidance back to the diffusion process via GS-based Reference Feature Warping for multi-view consistency, and finally applies a Texture-Enhancing Discriminator to refine photometric realism.

What carries the argument

The multi-stage consistency pipeline consisting of 2D diffusion, Reference Adaptive GS, GS-based Reference Feature Warping, and Texture-Enhancing Discriminator that enables bidirectional information flow between 2D and 3D.

If this is right

  • CoIn can perform 3D inpainting for object insertion as well as removal.
  • The method works with arbitrary-shaped masks rather than requiring precise multi-view segmentation.
  • State-of-the-art performance is achieved on 3D scene inpainting tasks through the bidirectional guidance.
  • Multi-view consistency is maintained by using the 3D GS representation to guide 2D inpainting.

Where Pith is reading between the lines

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

  • The pipeline could extend to dynamic scenes if the Gaussian Splatting representation incorporates time information.
  • The warping and discriminator stages might adapt to other 3D editing tasks such as relighting or style transfer.
  • Evaluation on real captured scenes with natural occlusions would test whether the consistency holds outside controlled settings.

Load-bearing premise

The multi-stage consistency pipeline will produce multi-view consistent results without requiring precise multi-view segmentation masks.

What would settle it

Visible inconsistencies or artifacts across different viewpoints in the inpainted 3D scene when using loose or arbitrary masks on complex real-world scenes would falsify the central claim.

Figures

Figures reproduced from arXiv: 2606.27584 by Hana Kim, Minje Kim, Tae-Kyun Kim.

Figure 1
Figure 1. Figure 1: Key impact of inconsistent masks on 3D-first vs. 2D-first pipelines. [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of CoIn. We begin with initial 2D inpainting results and apply Reference GS with Feature Attention to obtain a coarse inpainted 3D scene. We then use Consistency Loss Guidance for the frozen latent diffusion inpainting model with GS￾based Reference Feature Warping, and the consistency-preserved results are finally used to fine-tune the 3D Gaussian Splatting scene G with a Texture-Enhancing Discrim… view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative results on the SPIn-NeRF dataset [28] [PITH_FULL_IMAGE:figures/full_fig_p010_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative results on the IMFine dataset [37] [PITH_FULL_IMAGE:figures/full_fig_p012_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative results for object insertion task. [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Results of ablation studies (A) Qualitative results for ablation studies on the “Book" scene of SPIn-NeRF dataset [28]. We mark inpainted regions with red boxes and especially highlight inconsistencies with yellow circles. Rows (a)–(d) show w/o Ref￾GS, w/o CLG, w/o TE-D, and the full model, respectively. (B) Depth map comparison on the “Dabao" scene from the IMFine dataset [37]. We highlight the inpainted … view at source ↗
Figure 1
Figure 1. Figure 1: Qualitative comparison of 2D-first and 3D-first pipelines. The 3D-first pipeline simplifies inpainting by targeting only truly occluded areas, unlike the more challenging 2D-first approach with its larger mask. With Segmentation Mask With Bounding Box Mask Input Novel View 1 Novel View 2 Novel View 3 “ A green apple” “ Cactus” “White flour pack” [PITH_FULL_IMAGE:figures/full_fig_p024_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative results. (a) Input views and 3D-inconsistent masks from 2D segmentation. (b) Irregular masks with original inputs (left) and our consistent novel views (right). (c) Failure cases: large masks with view changes beyond 180◦ (left) lead to blurry textures (right) [PITH_FULL_IMAGE:figures/full_fig_p024_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Additional qualitative results on the SPIn-NeRF dataset [S1] [PITH_FULL_IMAGE:figures/full_fig_p025_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Additional qualitative results on the IMFine dataset [S2] [PITH_FULL_IMAGE:figures/full_fig_p026_5.png] view at source ↗
read the original abstract

3D scene inpainting is essential for reconstructing areas corrupted by occlusions or limited viewpoints. While recent methods leverage Gaussian Splatting (GS) for efficient 3D editing, they often depend on precise multi-view segmentation masks and are inherently constrained to object removal tasks. We propose CoIn, a novel framework that bridges 2D inpainting models and 3DGS through a multi-stage consistency pipeline. Our approach first generates initial inpainted images using a diffusion model, enabling the use of arbitrary-shaped masks and diverse tasks like object insertion. We then introduce Reference Adaptive GS with Feature Attention to reconstruct a coarse 3D scene by adaptively weighing towards a reference view (2D -> 3D). This 3D representation provides geometric guidance to the diffusion process via GS-based Reference Feature Warping, ensuring multi-view consistency (3D -> 2D). Finally, a Texture-Enhancing Discriminator refines the 3D scene to achieve high photometric realism (2D -> 3D). Experiments show that CoIn, effectively leveraging bidirectional information flow, achieves state-of-the-art performance and effectively handles both object removal and object insertion with flexible mask input.

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.

Referee Report

0 major / 3 minor

Summary. The paper proposes CoIn, a framework for 3D scene inpainting that integrates 2D diffusion models with 3D Gaussian Splatting via a multi-stage bidirectional pipeline: 2D diffusion generates initial inpainted images from arbitrary masks (supporting removal and insertion), Reference Adaptive GS with Feature Attention reconstructs a coarse 3D scene (2D->3D), GS-based Reference Feature Warping provides geometric guidance back to the diffusion process for multi-view consistency (3D->2D), and a Texture-Enhancing Discriminator refines photometric quality (2D->3D). Experiments are reported to demonstrate SOTA performance on both object removal and insertion tasks.

Significance. If the bidirectional consistency mechanism holds, the work would meaningfully extend GS-based editing by relaxing the need for precise multi-view segmentation masks and enabling insertion tasks, which prior methods largely exclude. The pipeline's explicit 2D-3D feedback loop is a clear technical contribution over unidirectional approaches.

minor comments (3)
  1. The abstract and introduction would benefit from explicit citation of the specific datasets, baselines, and quantitative metrics (e.g., PSNR, LPIPS, or perceptual scores) used to support the SOTA claim, as these are referenced only qualitatively.
  2. Notation for the Reference Adaptive GS (e.g., how the feature attention weights are computed and normalized) is introduced without an accompanying equation or pseudocode block, which would aid reproducibility.
  3. Figure captions for the pipeline diagram and qualitative results should include the exact mask types (arbitrary vs. multi-view) and view counts shown to make the consistency claims easier to inspect.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary of our work, the recognition of the bidirectional 2D-3D pipeline as a technical contribution, and the recommendation for minor revision. No major comments were listed in the report.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The provided abstract and description contain no equations, fitted parameters, predictions, or derivation steps. The method is presented as a multi-stage pipeline (2D diffusion to Reference Adaptive GS to warping to discriminator) whose performance is evaluated empirically. No self-definitional relations, fitted inputs renamed as predictions, or load-bearing self-citations appear in the text. The central claim of multi-view consistency via bidirectional flow is an engineering description rather than a mathematical reduction to its own inputs, making the result self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only; no free parameters, axioms, or invented entities are specified or derivable from the provided text.

pith-pipeline@v0.9.1-grok · 5743 in / 1109 out tokens · 27088 ms · 2026-06-29T01:23:04.677791+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

75 extracted references · 12 canonical work pages · 6 internal anchors

  1. [1]

    Spin-nerf: Multiview segmentation and perceptual inpainting with neural radiance fields

    Ashkan Mirzaei, Tristan Aumentado-Armstrong, Konstantinos G Derpanis, Jonathan Kelly, Marcus A Brubaker, Gilitschenski, and Alex Levinshtein. Spin-nerf: Multiview segmentation and perceptual inpainting with neural radiance fields. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20669–20679, 2023

    2023

  2. [2]

    Imfine: 3d inpainting via geometry-guided multi-view refinement

    Zhihao Shi, Dong Huo, Yuhongze Zhou, Yan Min, Juwei Lu, and Xinxin Zuo. Imfine: 3d inpainting via geometry-guided multi-view refinement. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 26694-26703, 2025

    2025

  3. [3]

    Learning 3d geometry and feature consistent gaussian splatting for object removal

    Yuxin Wang, Qianyi Wu, Guofeng Zhang, and Dan Xu. Learning 3d geometry and feature consistent gaussian splatting for object removal. In European Conference on Computer Vision, pages 1–17. Springer, 2024

    2024

  4. [4]

    3d gaussian inpainting with depth-guided cross-view consistency

    Sheng-Yu Huang, Zi-Ting Chou, and Yu-Chiang Frank Wang. 3d gaussian inpainting with depth-guided cross-view consistency. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 26704–26713, 2025

    2025

  5. [5]

    Structure-from-motion revisited

    Johannes L Schonberger and Jan-Michael Frahm. Structure-from-motion revisited. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4104–4113, 2016

    2016

  6. [6]

    High-resolution image synthesis with latent diffusion models

    Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj¨orn Ommer. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022

    2022

  7. [7]

    Gaussian grouping: Segment and edit anything in 3d scenes

    Mingqiao Ye, Martin Danelljan, Fisher Yu, and Lei Ke. Gaussian grouping: Segment and edit anything in 3d scenes. In European conference on computer vision, pages 162–179. Springer, 2024

    2024

  8. [10]

    Gaussianeditor: Swift and controllable 3d editing with gaussian splatting

    Chen, Yiwen, et al. "Gaussianeditor: Swift and controllable 3d editing with gaussian splatting." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024

    2024

  9. [12]

    and Kim, T.-K

    Kim, J. and Kim, T.-K. , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

  10. [13]

    FirstName Alpher , title =

  11. [14]

    Journal of Foo , volume = 13, number = 1, pages =

    FirstName Alpher and FirstName Fotheringham-Smythe , title =. Journal of Foo , volume = 13, number = 1, pages =

  12. [15]

    Journal of Foo , volume = 14, number = 1, pages =

    FirstName Alpher and FirstName Fotheringham-Smythe and FirstName Gamow , title =. Journal of Foo , volume = 14, number = 1, pages =

  13. [16]

    FirstName Alpher and FirstName Gamow , title =

  14. [17]

    Computer Vision -- ECCV 2022 , year =

    2022

  15. [18]

    2020 , booktitle=

    NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis , author=. 2020 , booktitle=

    2020

  16. [19]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Scaffold-gs: Structured 3d gaussians for view-adaptive rendering , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

  17. [20]

    , author=

    3D Gaussian splatting for real-time radiance field rendering. , author=. ACM Trans. Graph. , volume=

  18. [21]

    Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

    Imfine: 3d inpainting via geometry-guided multi-view refinement , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

  19. [22]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Spin-nerf: Multiview segmentation and perceptual inpainting with neural radiance fields , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

  20. [23]

    European Conference on Computer Vision , pages=

    Taming latent diffusion model for neural radiance field inpainting , author=. European Conference on Computer Vision , pages=. 2024 , organization=

    2024

  21. [24]

    Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

    3d gaussian inpainting with depth-guided cross-view consistency , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

  22. [25]

    European Conference on Computer Vision , pages=

    Learning 3d geometry and feature consistent gaussian splatting for object removal , author=. European Conference on Computer Vision , pages=. 2024 , organization=

    2024

  23. [26]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Mvip-nerf: Multi-view 3d inpainting on nerf scenes via diffusion prior , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

  24. [27]

    Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

    Met3r: Measuring multi-view consistency in generated images , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

  25. [28]

    Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

    Freedom: Training-free energy-guided conditional diffusion model , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

  26. [29]

    Proceedings of the IEEE/CVF international conference on computer vision , pages=

    Emerging properties in self-supervised vision transformers , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=

  27. [30]

    arXiv preprint arXiv:2403.10516 , year=

    Featup: A model-agnostic framework for features at any resolution , author=. arXiv preprint arXiv:2403.10516 , year=

    work page arXiv

  28. [31]

    European conference on computer vision , pages=

    Gaussian grouping: Segment and edit anything in 3d scenes , author=. European conference on computer vision , pages=. 2024 , organization=

    2024

  29. [32]

    Proceedings of the IEEE/CVF international conference on computer vision , pages=

    Reference-guided controllable inpainting of neural radiance fields , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=

  30. [33]

    Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

    The unreasonable effectiveness of deep features as a perceptual metric , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

  31. [34]

    Advances in neural information processing systems , volume=

    Gans trained by a two time-scale update rule converge to a local nash equilibrium , author=. Advances in neural information processing systems , volume=

  32. [35]

    Proceedings of the IEEE/CVF winter conference on applications of computer vision , pages=

    Resolution-robust large mask inpainting with fourier convolutions , author=. Proceedings of the IEEE/CVF winter conference on applications of computer vision , pages=

  33. [36]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Repaint: Inpainting using denoising diffusion probabilistic models , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  34. [37]

    Classifier-Free Diffusion Guidance

    Ho, Jonathan and Salimans, Tim , title =. arXiv preprint arXiv:2207.12598 , year =

    work page internal anchor Pith review Pith/arXiv arXiv

  35. [38]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    High-resolution image synthesis with latent diffusion models , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  36. [39]

    arXiv preprint arXiv:2307.00407 , year=

    Wavepaint: Resource-efficient token-mixer for self-supervised inpainting , author=. arXiv preprint arXiv:2307.00407 , year=

    work page arXiv

  37. [40]

    European Conference on Computer Vision , pages=

    Brushnet: A plug-and-play image inpainting model with decomposed dual-branch diffusion , author=. European Conference on Computer Vision , pages=. 2024 , organization=

    2024

  38. [41]

    arXiv preprint arXiv:2312.04831 , year=

    Towards Context-Stable and Visual-Consistent Image Inpainting , author=. arXiv preprint arXiv:2312.04831 , year=

    work page arXiv

  39. [42]

    European Conference on Computer Vision , pages=

    Objectdrop: Bootstrapping counterfactuals for photorealistic object removal and insertion , author=. European Conference on Computer Vision , pages=. 2024 , organization=

    2024

  40. [43]

    ACM SIGGRAPH 2022 conference proceedings , pages=

    Palette: Image-to-image diffusion models , author=. ACM SIGGRAPH 2022 conference proceedings , pages=

    2022

  41. [44]

    arXiv preprint arXiv:2408.08000 , year=

    Mvinpainter: Learning multi-view consistent inpainting to bridge 2d and 3d editing , author=. arXiv preprint arXiv:2408.08000 , year=

    work page arXiv

  42. [45]

    Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

    Editsplat: Multi-view fusion and attention-guided optimization for view-consistent 3d scene editing with 3d gaussian splatting , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

  43. [46]

    Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

    Instant3dit: Multiview inpainting for fast editing of 3d objects , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

  44. [47]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Consistdreamer: 3d-consistent 2d diffusion for high-fidelity scene editing , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

  45. [48]

    DreamFusion: Text-to-3D using 2D Diffusion

    Dreamfusion: Text-to-3d using 2d diffusion , author=. arXiv preprint arXiv:2209.14988 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  46. [49]

    Proceedings of the seventh IEEE international conference on computer vision , volume=

    Texture synthesis by non-parametric sampling , author=. Proceedings of the seventh IEEE international conference on computer vision , volume=. 1999 , organization=

    1999

  47. [50]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Universal guidance for diffusion models , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  48. [51]

    , author=

    Lora: Low-rank adaptation of large language models. , author=. ICLR , volume=

  49. [52]

    IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

    Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models , author=. arXiv preprint arXiv:2308.06721 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  50. [53]

    Proceedings of the AAAI conference on artificial intelligence , volume=

    T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models , author=. Proceedings of the AAAI conference on artificial intelligence , volume=

  51. [54]

    International Conference on Machine Learning , pages=

    Loss-guided diffusion models for plug-and-play controllable generation , author=. International Conference on Machine Learning , pages=. 2023 , organization=

    2023

  52. [55]

    European Conference on Computer Vision , pages=

    High-fidelity image inpainting with gan inversion , author=. European Conference on Computer Vision , pages=. 2022 , organization=

    2022

  53. [56]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Gaussianeditor: Swift and controllable 3d editing with gaussian splatting , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  54. [57]

    Proceedings of the IEEE/CVF international conference on computer vision , pages=

    Instruct-nerf2nerf: Editing 3d scenes with instructions , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=

  55. [58]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Nerfiller: Completing scenes via generative 3d inpainting , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

  56. [59]

    Advances in Neural Information Processing Systems , volume=

    Depth anything v2 , author=. Advances in Neural Information Processing Systems , volume=

  57. [60]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Repurposing diffusion-based image generators for monocular depth estimation , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  58. [61]

    Advances in neural information processing systems , volume=

    Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction , author=. Advances in neural information processing systems , volume=

  59. [62]

    Proceedings of the 31st ACM International Conference on Multimedia , pages=

    MV-Diffusion: Motion-aware video diffusion model , author=. Proceedings of the 31st ACM International Conference on Multimedia , pages=

  60. [63]

    and Zhang, K

    Wang, T. and Zhang, K. and Shao, Z. and Luo, W. and Stenger, B. and Lu, T. and Kim, T.-K. and Liu, W. and Li, H. , title =. International Journal of Computer Vision (IJCV) , volume =

  61. [64]

    MVDream: Multi-view Diffusion for 3D Generation

    Mvdream: Multi-view diffusion for 3d generation , author=. arXiv preprint arXiv:2308.16512 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  62. [65]

    Proceedings of the IEEE/CVF international conference on computer vision , pages=

    Zero-1-to-3: Zero-shot one image to 3d object , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=

  63. [66]

    European Conference on Computer Vision , pages=

    Lgm: Large multi-view gaussian model for high-resolution 3d content creation , author=. European Conference on Computer Vision , pages=. 2024 , organization=

    2024

  64. [67]

    arXiv preprint arXiv:2304.10261 , year=

    Anything-3d: Towards single-view anything reconstruction in the wild , author=. arXiv preprint arXiv:2304.10261 , year=

    work page arXiv

  65. [68]

    and Cao, Z

    Ai, H. and Cao, Z. and Lu, H. and Chen, C. and Ma, J. and Zhou, P. and Kim, T.-K. and Hui, P. and Wang, L. , title =. IEEE Transactions on Visualization and Computer Graphics , volume =. 2024 , note =

    2024

  66. [69]

    Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

    Structure-from-motion revisited , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

  67. [70]

    Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

    Image-to-image translation with conditional adversarial networks , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

  68. [71]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Control4d: Efficient 4d portrait editing with text , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

  69. [72]

    Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

    Aurafusion360: Augmented unseen region alignment for reference-based 360deg unbounded scene inpainting , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

  70. [73]

    SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

    Sdxl: Improving latent diffusion models for high-resolution image synthesis , author=. arXiv preprint arXiv:2307.01952 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  71. [74]

    SAM 2: Segment Anything in Images and Videos

    Sam 2: Segment anything in images and videos , author=. arXiv preprint arXiv:2408.00714 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  72. [75]

    arXiv preprint arXiv:2404.11613 , year=

    Infusion: Inpainting 3d gaussians via learning depth completion from diffusion prior , author=. arXiv preprint arXiv:2404.11613 , year=

    work page arXiv

  73. [76]

    ACM Transactions on Graphics (ToG) , volume=

    Tip-editor: An accurate 3d editor following both text-prompts and image-prompts , author=. ACM Transactions on Graphics (ToG) , volume=. 2024 , publisher=

    2024

  74. [77]

    Advances in Neural Information Processing Systems (NIPS) , year =

    Kim, Minje and Kim, Tae-Kyun , title =. Advances in Neural Information Processing Systems (NIPS) , year =

  75. [78]

    Pattern Recognition , volume=

    LLDiffusion: Learning degradation representations in diffusion models for low-light image enhancement , author=. Pattern Recognition , volume=. 2025 , publisher=

    2025