Research map / 3D vision / Human pose estimation
From Image Collections to Point Clouds With Self-Supervised Shape and Pose Networks
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 |
|---|---|---|---|
| Add geometric and pose cycle consistency losses (ablation) | Self-supervised reconstruction network · ShapeNet Car | Chamfer: 10.33 -> 6.39 | Helped |
| Add geometric and pose cycle consistency losses (ablation) | Self-supervised reconstruction network · ShapeNet Chair | Chamfer: 21.84 -> 13.58 | Helped |
| Add geometric and pose cycle consistency losses (ablation) | Self-supervised reconstruction network · ShapeNet Aero | Chamfer: 15.06 -> 8.66 | Helped |
| Add nearest-neighbour consistency (ablation) | Ours-CC · ShapeNet Chair | Chamfer: 13.58 -> 10.91 | Helped |
| Add nearest-neighbour consistency (ablation) | Ours-CC · ShapeNet Aero | Chamfer: 8.66 -> 7.11 | Helped |
| Use more than 3 nearest-neighbour images in the loss (ablation) | Nearest-neighbour consistency · ShapeNet | Chamfer | Hurt |
| Add symmetry loss (ablation) | Ours-NN · ShapeNet Aero | Chamfer: 7.91 -> 7.11 | Helped |
| Add symmetry loss (ablation) | Ours-NN · ShapeNet Chair | Chamfer: 10.91 -> 12.34 | Hurt |
| Add symmetry loss (ablation) | Ours-NN · ShapeNet Car | Chamfer: 5.48 -> 5.72 | Hurt |
| Apply inference-stage optimization (ablation) | Ours-NN · ShapeNet Chair | Chamfer: 10.91 -> 15.32 | Hurt |
| Apply geometric cycle consistency loss (ablation) | DIFFER · ShapeNet Chair | Chamfer: 9.78 -> 9.23 | Helped |
| Apply geometric cycle consistency loss (ablation) | ULSP_Sup · ShapeNet Aero | Chamfer: 5.70 -> 7.37 | Hurt |
Closest papers by meaning
- A Point Set Generation Network for 3D Object Reconstruction From a Single Image (CVPR 2017 · similarity 0.90)
- MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image (AAAI 2019 · similarity 0.89)
- Multi-View Representation is What You Need for Point-Cloud Pre-Training (ICLR 2024 · similarity 0.88)
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.87)
- Point2Real: Bridging the Gap between Point Cloud and Realistic Image for Open-World 3D Recognition (AAAI 2024 · similarity 0.86)
- Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025 · 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.