Research map / 3D vision / 3D generation
Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts
shuangkang fang, Yufeng Wang, Yi-Hsuan Tsai, Yi Yang, Wenrui Ding, Shuchang Zhou, Ming-Hsuan Yang
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 |
|---|---|---|---|
| replace LNA atlas mapping with Hash-Atlas | atlas construction · LLFF atlas reconstruction | PSNR: 23.04 -> 24.66 | Improved |
| replace LNA with Hash-Atlas for training time | atlas construction · LLFF atlas reconstruction | Train time (h): 10.75 -> 0.60 | Improved |
| add initial position and alpha pre-training losses (L_init) (ablation) | Hash-Atlas / CE3D · LLFF editing | CLIP score: 0.242 -> 0.304 | Improved |
| add inpainting reconstruction loss L_rec^pro (ablation) | Hash-Atlas / CE3D · CE3D-collect editing | CLIP score: 0.263 -> 0.352 | Improved |
| add scene-name handling (SSN) in dialog system (ablation) | CE3D · LLFF editing | CLIP score | Improved |
| add Executor merge-split strategy for editing atlases (ablation) | CE3D · LLFF editing | CLIP score: 0.190 -> 0.304 | Improved |
| add Executor merge-split strategy on CDS (ablation) | CE3D · CE3D-collect editing | CDS: 0.201 -> 0.248 | Improved |
| apply atlas editing to 360-degree scenes | CE3D · 360-degree scenes | editing success | Hurt |
Closest papers by meaning
- EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing (ICLR 2025 · similarity 0.88)
- Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts (ICLR 2024 · similarity 0.87)
- Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers (NeurIPS 2024 · similarity 0.87)
- 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting (ICLR 2025 · similarity 0.87)
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.87)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 2025 · similarity 0.86)
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.
