Research map / 3D vision / Face and shape
CAPRI-Net: Learning Compact CAD Shapes With Adaptive Primitive Assembly
Check 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 CAPRI-Net instead of UCSG for voxel reconstruction | ABC voxel reconstruction · ABC | CD: 0.182 -> 0.148 | Helped |
| Use CAPRI-Net instead of BSP-Net for voxel reconstruction | ShapeNet voxel reconstruction · ShapeNet | NC: 0.867 -> 0.850 | Hurt |
| Use CAPRI-Net instead of BSP-Net for point-cloud reconstruction | ABC · ABC point-cloud reconstruction | CD: 0.19 -> 0.09 | Helped |
| Add quadric-surface primitives (ablation) | CAPRI-Net · ABC | CD: 0.34 -> 0.15 | Helped |
| Add the difference layer (ablation) | CAPRI-Net · ABC | CD: 0.29 -> 0.15 | Helped |
| Add weighted reconstruction loss (ablation) | CAPRI-Net · ABC | CD: 0.26 -> 0.15 | Helped |
| Fine-tune the pretrained network for each test shape | CAPRI-Net · ABC voxel reconstruction | CD: 0.56 -> 0.15 | Helped |
Closest papers by meaning
- D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts (NeurIPS 2023 · similarity 0.91)
- Neural Parts: Learning Expressive 3D Shape Abstractions With Invertible Neural Networks (CVPR 2021 · similarity 0.89)
- MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans (NeurIPS 2025 · similarity 0.86)
- cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning (ICLR 2026 · similarity 0.86)
- CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention (CVPR 2024 · similarity 0.86)
- Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds (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.