Research map / 3D vision / 3D generation
DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
Qingcheng Zhao, Xiang Zhang, Haiyang Xu, Zeyuan Chen, Jianwen Xie, Yuan Gao, Zhuowen Tu
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 depth-guided conditioning (ablation) | DepR · 3D-FRONT object-level | F-score: 61.90 -> 89.66 | Improved |
| add local-global attention (ablation) | DepR · 3D-FRONT object-level | F-score: 87.36 -> 89.66 | Improved |
| add depth-guided DDIM sampling (ablation) | DepR · 3D-FRONT object-level | F-score: 89.64 -> 89.66 | Improved |
| use ground-truth layout in depth-guided sampling (ablation) | DepR · 3D-FRONT object-level | F-score: 89.66 -> 89.92 | Improved |
| use ground-truth depth for conditioning (ablation) | DepR · 3D-FRONT object-level | F-score: 89.66 -> 90.24 | Improved |
| use ground-truth segmentation instead of Grounded-SAM masks (ablation) | DepR · 3D-FRONT scene-level | F-score: 24.63 -> 30.47 | Improved |
| use ground-truth depth instead of estimated depth for scene layout (ablation) | DepR · 3D-FRONT scene-level | F-score: 24.63 -> 26.09 | Improved |
| use ground-truth depth for scene layout (single-direction Chamfer) (ablation) | DepR · 3D-FRONT scene-level | CD-S: 57.3 -> 61.4 | Hurt |
| use ground-truth layout (ablation) | DepR · 3D-FRONT scene-level | F-score: 30.47 -> 67.65 | Improved |
| enable depth-guided sampling (inference time) (ablation) | DepR · 3D-FRONT runtime | runtime: about 20 s -> about 1.2 min per scene | Hurt |
Later papers that compared with this method
1 later accepted paper reports DepR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction (CVPR 2026 · better on 4 of 6 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
- Coherent 3D Scene Diffusion From a Single RGB Image (NeurIPS 2024 · similarity 0.89)
- Decompositional Neural Scene Reconstruction with Generative Diffusion Prior (CVPR 2025 · similarity 0.88)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · similarity 0.88)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.88)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.87)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 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.
