Research map / 3D vision / Gaussian splatting
CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance
Hana Kim, Minje Kim, Tae-Kyun Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Ref-GS (reference adaptive GS with feature attention) (ablation) | CoIn · SPIn-NeRF | FID: 30.47 -> 28.92 | Improved |
| add adaptive weight in Ref-GS (ablation) | CoIn · SPIn-NeRF | FID: 30.76 -> 28.92 | Improved |
| add feature attention in Ref-GS (ablation) | CoIn · SPIn-NeRF | FID: 31.78 -> 28.92 | Improved |
| add Consistency Loss Guidance (CLG) (ablation) | CoIn · SPIn-NeRF | FID: 36.47 -> 28.92 | Improved |
| add Texture-Enhancing Discriminator (TE-D) (ablation) | CoIn · SPIn-NeRF | FID: 39.31 -> 28.92 | Improved |
| add Texture-Enhancing Discriminator (TE-D) (ablation) | CoIn · SPIn-NeRF | m-FID: 132.55 -> 80.44 | Improved |
| add CLG (ablation) | CoIn · SPIn-NeRF | LPIPS: 0.3057 -> 0.2349 | Improved |
| use bounding-box mask instead of segmentation mask (ablation) | CoIn · IMFine dataset | FID: 53.37 -> 61.38 | Hurt |
| use 3D-first pipeline instead of 2D-first on 360 scenes (ablation) | CoIn · IMFine 360 scenes | FID: 53.02 -> 48.67 | Improved |
| use 3D-first pipeline instead of 2D-first on 360 scenes (ablation) | CoIn · IMFine 360 scenes | PSNR: 22.33 -> 22.67 | Improved |
| use irregular mask instead of segmentation mask (ablation) | CoIn · SPIn-NeRF scene 10 | FID: 17.28 -> 19.88 | No clear effect |
| use bounding-box mask instead of segmentation mask (ablation) | CoIn · SPIn-NeRF scene 10 | FID: 17.28 -> 17.93 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- IMFine — IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement (CVPR 2025) · better on 3 of 3 shared results
- MVIP-NeRF — MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior (CVPR 2024) · better on 2 of 2 shared results
- Gaussian Grouping — Gaussian Grouping: Segment and Edit Anything in 3D Scenes (ECCV 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GPGS: Consistent 3D Object Removal via Geometry-Aware 3D Inpainting and Projected Image Refinement in 3D Gaussian Splatting (AAAI 2026 · similarity 0.89)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model (NeurIPS 2025 · similarity 0.87)
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.87)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 2025 · similarity 0.87)
- 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
