Research map / 3D vision / 3D generation
Edit360: 2D Image Edits to 3D Assets from Any Angle
Junchao Huang, Xinting Hu, Shaoshuai Shi, Zhuotao Tian, Li Jiang
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 Spatial Progressive Fusion over linear-interpolation baseline (ablation) | Edit-SV3D · GSO ablation | LPIPS: 0.11 -> 0.08 | Improved |
| add Spatial Progressive Fusion over linear-interpolation baseline (ablation) | Edit-SV3D · GSO ablation | PSNR: 20.57 -> 20.90 | Improved |
| add Spatial Progressive Fusion over linear-interpolation baseline (ablation) | Edit-SV3D · GSO ablation | SSIM: 0.83 -> 0.87 | Improved |
| add Spatial Progressive Fusion over linear-interpolation baseline (ablation) | Edit-SV3D · GSO ablation | CLIP-S: 0.85 -> 0.85 | No clear effect |
| add Cross-View Alignment on top of SPF (ablation) | Edit-SV3D · GSO ablation | PSNR: 20.90 -> 22.17 | Improved |
| add Cross-View Alignment on top of SPF (ablation) | Edit-SV3D · GSO ablation | LPIPS: 0.08 -> 0.07 | Improved |
| add Cross-View Alignment on top of SPF (ablation) | Edit-SV3D · GSO ablation | SSIM: 0.87 -> 0.90 | Improved |
| add Cross-View Alignment on top of SPF (ablation) | Edit-SV3D · GSO ablation | CLIP-S: 0.85 -> 0.88 | Improved |
| add Cross-View Alignment on top of SPF (ablation) | Edit-SV3D · GSO ablation | MSE: 0.02 -> 0.02 | No clear effect |
| add an extra anchor view v^i to SV3D with Edit360 | SV3D · GSO | PSNR: 21.14 -> 22.17 | Improved |
| add an extra anchor view v^i to SV3D with Edit360 | SV3D · OmniObject3D | PSNR: 19.68 -> 20.44 | Improved |
| provide two ground-truth views instead of a generated anchor view | Edit-SV3D · GSO | PSNR: 22.17 -> 26.32 | Improved |
Later papers that compared with this method
1 later accepted paper reports Edit360 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- 3D-LATTE: Latent Space 3D Editing from Textual Instructions (CVPR 2026 · better on 3 of 3 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
- Coupled Diffusion Sampling for Training-Free Multi-View Image Editing (CVPR 2026 · similarity 0.91)
- 3D-LATTE: Latent Space 3D Editing from Textual Instructions (CVPR 2026 · similarity 0.90)
- SyncNoise: Geometrically Consistent Noise Prediction for Instruction-based 3D Editing (AAAI 2025 · similarity 0.89)
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing (ICLR 2025 · similarity 0.87)
- ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing (CVPR 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.
