Research map / 3D vision / 3D generation
Fast Multi-view Consistent 3D Editing with Video Priors
Liyi Chen, Ruihuang Li, Guowen Zhang, Pengfei Wang, Lei Zhang
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 continuous rendered views (ablation) | ViP3DE · 3D editing ablation | CLIP text-image similarity: 0.198 -> 0.220 | Improved |
| add continuous rendered views (ablation) | ViP3DE · 3D editing ablation | CLIP directional similarity: 0.083 -> 0.109 | Improved |
| add motion-preserved noise blending (ablation) | ViP3DE with continuous views · 3D editing ablation | CLIP text-image similarity: 0.220 -> 0.271 | Improved |
| add motion-preserved noise blending (ablation) | ViP3DE with continuous views · 3D editing ablation | CLIP directional similarity: 0.109 -> 0.185 | Improved |
| add geometry-aware denoising (ablation) | ViP3DE with continuous views and noise blending · 3D editing ablation | CLIP text-image similarity: 0.271 -> 0.284 | Improved |
| add geometry-aware denoising (ablation) | ViP3DE with continuous views and noise blending · 3D editing ablation | CLIP directional similarity: 0.185 -> 0.197 | Improved |
| add motion-preserved noise blending (ablation) | ViP3DE with continuous views and geometry-aware denoising · 3D editing ablation | CLIP text-image similarity: 0.258 -> 0.284 | Improved |
| use video priors with noise blending and geometry-aware denoising instead of DGE's 2D-model correspondence | ViP3DE vs DGE · 3D editing (Mip-NeRF360 and LLFF subset) | CLIP text-image similarity: 0.269 -> 0.284 | Improved |
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.
- GaussCtrl — GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing (ECCV 2024) · better on 2 of 2 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
- SyncNoise: Geometrically Consistent Noise Prediction for Instruction-based 3D Editing (AAAI 2025 · similarity 0.91)
- Towards Scalable and Consistent 3D Editing (ICML 2026 · similarity 0.89)
- Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing (ECCV 2026 · similarity 0.89)
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- PrEditor3D: Fast and Precise 3D Shape Editing (CVPR 2025 · similarity 0.87)
- VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors (CVPR 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.
