Research map / 3D vision / 3D generation
Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors
Ruicheng Wang, Jianfeng Xiang, Jiaolong Yang, Xin Tong
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 |
|---|---|---|---|
| use diffusion-based 3D editing with depth warping instead of OBJect-3DIT, Zero123 or Stable-Zero123 | Ours · Single-image 3D editing benchmark | LPIPS: 0.132 -> 0.102 | Improved |
| run iteration 3 instead of stopping at iteration 1 (ablation) | Ours · Single-image 3D editing benchmark | Confident Area: 0.235 -> 0.356 | Improved |
| run iteration 3 instead of stopping at iteration 1 (ablation) | Ours · Single-image 3D editing benchmark | Perceptual Similarity: 0.890 -> 0.905 | Improved |
| add LoRA tuning to the undistortion phase (ablation) | Ours · undistortion ablation (first iteration) | visual layout and consistency | Improved |
| use noise-free DDIM inversion instead of noise addition in undistortion (ablation) | Ours · undistortion ablation (first iteration) | appearance consistency | Improved |
| user study versus other three methods | Ours · User study | preference rate (%): 71.36% | Improved |
Closest papers by meaning
- Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D (CVPR 2024 · similarity 0.91)
- SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D (ICLR 2024 · similarity 0.90)
- Generating Images with 3D Annotations Using Diffusion Models (ICLR 2024 · similarity 0.90)
- In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment (NeurIPS 2024 · similarity 0.90)
- SyncNoise: Geometrically Consistent Noise Prediction for Instruction-based 3D Editing (AAAI 2025 · similarity 0.89)
- Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation (CVPR 2025 · similarity 0.89)
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.
