Research map / 3D vision / Gaussian splatting
DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
Minghao Chen, Iro Laina, Andrea Vedaldi
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 multi-view consistent editing (spatio-temporal attention) on top of epipolar feature injection (ablation) | DGE · 3D text-guided editing | CLIP Score: 0.221 -> 0.226 | Improved |
| add epipolar constraints in feature injection (ablation) | DGE · 3D text-guided editing | CLIP Score: 0.203 -> 0.221 | Improved |
| add multi-view consistent editing and epipolar constraints together (ablation) | DGE · 3D text-guided editing | CLIP Directional Score: 0.059 -> 0.067 | Improved |
| direct fitting to consistent edits instead of iterative dataset updates, with Gaussian Splatting | DGE · 3D text-guided editing | Avg. editing time: ~ 7min -> ~ 4min (vs GaussianEditor) | Improved |
| use multi-view consistent editing instead of SDS with IP2P on GS | DGE · 3D text-guided editing | CLIP Similarity: 0.206 -> 0.226 | Improved |
| switch from NeRF to 3D Gaussian Splatting in editing pipeline | text-guided 3D editing · 3D text-guided editing | Avg. editing time: ~ 51min -> ~ 7min (Instruct-N2N vs GaussianEditor) | Improved |
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.
- ViCA-NeRF — ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields (NeurIPS 2023) · 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
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation (CVPR 2025 · similarity 0.89)
- GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting (CVPR 2024 · similarity 0.88)
- Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields (CVPR 2024 · similarity 0.88)
- DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization (CVPR 2024 · similarity 0.87)
- D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup (NeurIPS 2024 · 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.
