Research map / 3D vision / Face and shape
Dense Human Body Correspondences Using Convolutional 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 non-rigid registration refinement to CNN descriptor matches (ablation) | CNN correspondences · FAUST intra-subject pairs | AE (cm): 5.65 -> 2.00 | Helped |
| add non-rigid registration refinement to CNN descriptor matches (ablation) | CNN correspondences · FAUST intra-subject pairs | 10cm-recall: 0.918 -> 0.975 | Helped |
| add non-rigid registration refinement to CNN descriptor matches (ablation) | CNN correspondences · FAUST inter-subject pairs | AE (cm): 5.73 -> 2.35 | Helped |
| add non-rigid registration refinement to CNN descriptor matches (ablation) | CNN correspondences · FAUST inter-subject pairs | 10cm-recall: 0.917 -> 0.972 | Helped |
| use multiple randomized segmentations to train a smooth descriptor embedding (ablation) | Dense Human Body Correspondences Using Convolutional Networks · FAUST | average correspondence error | Helped |
| train on body-region classification rather than directly optimizing correspondence pairs or triplets | Dense Human Body Correspondences Using Convolutional Networks · partial and full human-shape matching | correspondence robustness | Helped |
Closest papers by meaning
- BodyMap: Learning Full-Body Dense Correspondence Map (CVPR 2022 · similarity 0.92)
- DensePose: Dense Human Pose Estimation in the Wild (CVPR 2018 · similarity 0.91)
- HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences (CVPR 2021 · similarity 0.89)
- Human Shape From Silhouettes Using Generative HKS Descriptors and Cross-Modal Neural Networks (CVPR 2017 · similarity 0.89)
- 4D Human Body Correspondences From Panoramic Depth Maps (CVPR 2018 · similarity 0.89)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (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.