Research map / 3D vision / Face and shape
Learning to Infer and Execute 3D Shape Programs
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 |
|---|---|---|---|
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet table | IoU: 0.487 -> 0.591 | Helped |
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet chair | IoU: 0.422 -> 0.516 | Helped |
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet table | CD: 0.067 -> 0.058 | Helped |
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet chair | CD: 0.072 -> 0.063 | Helped |
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet bed | IoU: 0.234 -> 0.367 | Helped |
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet sofa | IoU: 0.296 -> 0.597 | Helped |
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet cabinet | IoU: 0.251 -> 0.478 | Helped |
| Apply guided adaptation using reconstruction loss through the frozen executor (ablation) | Shape Programs · ShapeNet bench | IoU: 0.176 -> 0.418 | Helped |
| Add the program-based completion and smoothing stage after MarrNet | MarrNet image-to-shape reconstruction · Pix3D | IoU | No clear effect |
| Add the program-based completion and smoothing stage after MarrNet | MarrNet image-to-shape reconstruction · Pix3D | participant preference: 78.9\% | Helped |
| Pretrain on simple synthetic program templates before guided adaptation | Shape Programs · ShapeNet | program inference and reconstruction | Helped |
Closest papers by meaning
- Neural Parts: Learning Expressive 3D Shape Abstractions With Invertible Neural Networks (CVPR 2021 · similarity 0.89)
- PLAD: Learning To Infer Shape Programs With Pseudo-Labels and Approximate Distributions (CVPR 2022 · similarity 0.89)
- Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image (CVPR 2020 · similarity 0.89)
- PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction (CVPR 2025 · similarity 0.88)
- RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures (CVPR 2022 · similarity 0.88)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 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.