Research map / 3D vision / Gaussian splatting
InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior
Minghao Wen, Shengjie Wu, Kangkan Wang, Dong Liang
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 CSCS reference view selection (ablation) | InterGSEdit · IN2N scenes (20 random views) | CLIP Similarity: 0.2034 -> 0.2090 | Improved |
| add CSCS reference view selection (ablation) | InterGSEdit · IN2N scenes (20 random views) | CTIDS: 0.1301 -> 0.1475 | Improved |
| add CSCS reference view selection (ablation) | InterGSEdit · IN2N scenes (20 random views) | CDC: 0.7647 -> 0.8218 | Improved |
| add AFN fusion of 3D-constrained and 2D attention (vs replacing 2D attention) (ablation) | InterGSEdit · IN2N scenes (20 random views) | CTIDS: 0.1243 -> 0.2738 | Improved |
| add AFN fusion of 3D-constrained and 2D attention (vs replacing 2D attention) (ablation) | InterGSEdit · IN2N scenes (20 random views) | CLIP Similarity: 0.2206 -> 0.2403 | Improved |
| add AFN fusion of 3D-constrained and 2D attention (vs replacing 2D attention) (ablation) | InterGSEdit · IN2N scenes (20 random views) | CDC: 0.8429 -> 0.8802 | Improved |
| add 3D geometry prior via AFN to pure 2D attention (ablation) | InterGSEdit · IN2N scenes (20 random views) | CLIP Similarity: 0.2252 -> 0.2403 | Improved |
| add 3D geometry prior via AFN to pure 2D attention (ablation) | InterGSEdit · IN2N scenes (20 random views) | CDC: 0.8616 -> 0.8802 | Improved |
| add 3D geometry prior via AFN to pure 2D attention (ablation) | InterGSEdit · IN2N scenes (20 random views) | CTIDS: 0.2835 -> 0.2738 | Hurt |
| use InfEdit diffusion backbone instead of ip2p | InterGSEdit · IN2N scenes (20 random views) | CTIDS: 0.1416 -> 0.1531 | Improved |
| use InfEdit diffusion backbone instead of ip2p | InterGSEdit · IN2N scenes (20 random views) | CDC: 0.8424 -> 0.8347 | Hurt |
| InterGSEdit versus GSEditor | InterGSEdit (InfEdit) · IN2N scenes (20 random views) | CLIP Similarity: 0.2169 -> 0.2285 | Improved |
Closest papers by meaning
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.93)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 2025 · similarity 0.90)
- 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting (ICLR 2025 · similarity 0.89)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.89)
- 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing (ICLR 2025 · similarity 0.89)
- SyncNoise: Geometrically Consistent Noise Prediction for Instruction-based 3D Editing (AAAI 2025 · similarity 0.89)
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.
