Research map / 3D vision / Gaussian splatting
GOR-IS: 3D Gaussian Object Removal In the Intrinsic Space
Yonghao Zhao, Yupeng Gao, Jian Yang, Jin Xie, Beibei Wang
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 explicit light transport modeling (ablation) | RaDe-GS baseline · GOR-IS-Synthetic | PSNR: 28.60 -> 31.44 | Improved |
| add explicit light transport modeling (ablation) | RaDe-GS baseline · GOR-IS-Synthetic | M-LPIPS: 0.099 -> 0.064 | Improved |
| add screen-space filtering (ablation) | GOR-IS with ELT · GOR-IS-Synthetic | PSNR: 31.44 -> 31.91 | Improved |
| add screen-space filtering (ablation) | GOR-IS with ELT · GOR-IS-Synthetic | FID: 25.7 -> 23.4 | Improved |
| add lighting-aware masking (ablation) | GOR-IS · GOR-IS-Synthetic | PSNR: 31.64 -> 31.91 | Improved |
| add lighting-aware masking (ablation) | GOR-IS · GOR-IS-Synthetic | M-LPIPS: 0.060 -> 0.060 | No clear effect |
| add material inpainting (ablation) | GOR-IS · GOR-IS-Synthetic | PSNR: 31.31 -> 31.91 | Improved |
| add material inpainting (ablation) | GOR-IS · GOR-IS-Synthetic | M-LPIPS: 0.075 -> 0.060 | Improved |
| add segmentation prior M_gt (ablation) | GOR-IS · GOR-IS-Synthetic | PSNR: 29.38 -> 31.91 | Improved |
| add normal prior N_gt (ablation) | GOR-IS · GOR-IS-Synthetic | PSNR: 29.77 -> 31.91 | Improved |
| replace LaMa with SD-1.5-Inpainting backbone (ablation) | GOR-IS · GOR-IS-Synthetic | PSNR: 31.91 -> 32.00 | No clear effect |
| replace LaMa with SD-1.5-Inpainting backbone (ablation) | GOR-IS · GOR-IS-Synthetic | M-LPIPS: 0.060 -> 0.066 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AuraFusion360 — AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpainting (CVPR 2025) · better on 3 of 3 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
- In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment (NeurIPS 2024 · similarity 0.88)
- InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields (CVPR 2024 · similarity 0.88)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.87)
- RNG: Relightable Neural Gaussians (CVPR 2025 · similarity 0.87)
- SplatFormer: Point Transformer for Robust 3D Gaussian Splatting (ICLR 2025 · similarity 0.87)
- GeoRemover: Removing Objects and Their Causal Visual Artifacts (NeurIPS 2025 · similarity 0.86)
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.
