Research map / 3D vision / 3D generation
VDFE: Difference-Aware 3D Scene Editing with Non-Intrusive Video Diffusion Priors for Multi-View Consistency and Efficiency
Chao Zhang, Fang Liu, Shuo Li, Yang Liu, Jiahao Wang, Xinyan Huang, Lingling Li, Puhua Chen, Xu Liu, Wenping Ma, Siqi Yu
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 FlowOCE optimal-control flow editing (ablation) | VDFE · 3D editing ablation | CLIP-dir: 0.1391 -> 0.1923 | Improved |
| add FlowOCE (ablation) | VDFE · 3D editing ablation | CLIP-sim: 0.2644 -> 0.2632 | No clear effect |
| add DFD flow-difference mask injection on top of FlowOCE (ablation) | VDFE · 3D editing ablation | CLIP-dir: 0.1923 -> 0.1929 | Improved |
| add DAGE difference-aware Gaussian editing (ablation) | VDFE · 3D editing ablation | CLIP-dir: 0.1929 -> 0.2051 | Improved |
| add DAGE (ablation) | VDFE · 3D editing ablation | CLIP-sim: 0.2647 -> 0.2662 | Improved |
| FlowOCE instead of Wan-Edit (FlowEdit-style) for video editing (ablation) | Wan2.1-T2V-1.3B · FiVE benchmark | Structure distance x10^3: 12.53 -> 5.68 | Improved |
| FlowOCE instead of Wan-Edit (ablation) | Wan2.1-T2V-1.3B · FiVE benchmark | FIVE-acc: 46.97 -> 54.87 | Improved |
| FlowOCE instead of Wan-Edit (ablation) | Wan2.1-T2V-1.3B · FiVE benchmark | CLIP Similarity: 26.39 -> 26.32 | No clear effect |
| add DFD to FlowOCE (ablation) | FlowOCE · FiVE benchmark | PSNR: 29.07 -> 29.43 | Improved |
| add DFD to FlowOCE (ablation) | FlowOCE · FiVE benchmark | FIVE-acc: 54.87 -> 52.68 | Hurt |
| VDFE vs EditSplat on 3D editing efficiency | 3DGS editing · 3D editing | iterations: ~1800 -> ~1600 | Improved |
| VDFE vs DGE on CLIP-sim | 3DGS editing · 3D editing | CLIP-sim: 0.2717 -> 0.2662 | Hurt |
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.
- EditSplat — EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025) · better on 4 of 4 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)
- ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing (NeurIPS 2024 · similarity 0.90)
- CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion (CVPR 2025 · similarity 0.90)
- Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion (CVPR 2024 · similarity 0.88)
- ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing (CVPR 2024 · similarity 0.88)
- Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training (CVPR 2024 · similarity 0.88)
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.
