Research map / 3D vision / Gaussian splatting
ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes
Jian Gao, Mengqi Yuan, Yifei Zeng, Chang Zeng, Zhihao Li, Zhenyu Chen, Weichao Qiu, Xiao-Xiao Long, Hao Zhu, Xun Cao, Yao Yao
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 |
|---|---|---|---|
| use SOPs instead of ray tracing for shadow computation (ablation) | ComGS · SynCom composition | rendering FPS: 3.48 -> 28.45 | Improved |
| use SOPs instead of ray tracing for shadows (ablation) | ComGS · SynCom composition | PSNR: 24.597 -> 24.456 | No clear effect |
| use SOPs instead of ray tracing for shadows (ablation) | ComGS · SynCom composition | editing time: 14.59 -> 36.12 | Hurt |
| use SOPs for inverse rendering instead of ray tracing | relightable Gaussian reconstruction · TensoIR | training time: 21.45 min -> 7.93 min (vs IRGS) | Improved |
| estimate lighting at the object placement from the Gaussian radiance field with fine-tuned diffusion (ablation) | ComGS · SynCom composition | PSNR: 21.842 -> 24.456 | Improved |
| add normal map to lighting estimation input (ablation) | lighting estimation model · lighting estimation ablation | scale-invariant RMSE: 0.067 -> 0.065 | Improved |
| increase mask coverage of reconstructed scene (ablation) | lighting estimation model · lighting estimation ablation | scale-invariant RMSE: 0.066 -> 0.052 | Improved |
| compare with R3DG that lacks indirect lighting supervision | relightable reconstruction · TensoIR NVS | NVS PSNR: 38.423 vs 35.822 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- IRGS — IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing (CVPR 2025) · better on 7 of 8 shared results
- GS-IR — GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024) · 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
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.92)
- GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024 · similarity 0.91)
- SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering (CVPR 2025 · similarity 0.90)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (CVPR 2025 · similarity 0.90)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.90)
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.
