Research map / 3D vision / 3D generation
Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 NPP instead of Bokhovkin et al. | Part decomposition and completion · Scan2CAD (ScanNet) | Chamfer Distance accuracy: 0.108 -> 0.074 | Helped |
| Use NPP instead of Bokhovkin et al. | Part decomposition and completion · Scan2CAD (ScanNet) | Chamfer Distance completion: 0.110 -> 0.092 | Helped |
| Add latent projection mapping initialization (ablation) | NPP · Scan2CAD (ScanNet) | Chamfer Distance accuracy: 0.160 -> 0.074 | Helped |
| Add synthetic pretraining (ablation) | NPP · Scan2CAD (ScanNet) | Chamfer Distance completion: 0.122 -> 0.092 | Helped |
| Add test-time optimization (ablation) | NPP · Scan2CAD (ScanNet) | Chamfer Distance accuracy: 0.093 -> 0.074 | Helped |
| Add full-shape constraint (ablation) | NPP test-time optimization · Scan2CAD (ScanNet) | Chamfer Distance completion: 0.101 -> 0.092 | Helped |
| Add dense part segmentation guidance (ablation) | NPP test-time optimization · Scan2CAD (ScanNet) | Chamfer Distance completion: 0.112 -> 0.092 | Helped |
| Add scene-consistency optimization (ablation) | NPP · Scan2CAD (ScanNet) | Chamfer Distance accuracy: 0.077 -> 0.074 | Helped |
Closest papers by meaning
- Towards Part-Based Understanding of RGB-D Scans (CVPR 2021 · similarity 0.91)
- Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image (CVPR 2020 · similarity 0.89)
- 3D Reconstruction with Generalizable Neural Fields using Scene Priors (ICLR 2024 · similarity 0.88)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.87)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.87)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · 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.