Research map / 3D vision / Face and shape
COAP: Compositional Articulated Occupancy of People
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 compositional part-aware occupancy instead of a holistic implicit field | COAP · PosePrior | IoU Surf.: LEAP 73.33; COAP 89.92 | Helped |
| use compositional part-aware occupancy instead of a holistic implicit field | COAP · DFaust | IoU Surf.: LEAP 66.35; COAP 84.44 | Helped |
| add a geometric prior for local body shape (ablation) | COAP · PosePrior sequences | IoU Surface: 82.81 -> 84.46 | Helped |
| add one-hot encoding for local features (ablation) | COAP · PosePrior sequences | IoU Surface: 82.81 -> 85.44 | Helped |
| add both geometric prior and one-hot encoding (ablation) | COAP · PosePrior sequences | IoU Surface: 82.81 -> 86.86 | Helped |
| add COAP collision term | PROX reconstruction · PROX quantitative dataset | Penetration: 143.52 -> 100.17 | Helped |
| add COAP collision term | PROX reconstruction · PROX quantitative dataset | V2V [mm]: 154.26 -> 154.15 | Helped |
| add COAP collision term | PROX reconstruction · PROX quantitative dataset | PJE [mm]: 154.39 -> 154.34 | Helped |
| use ground-truth scene SDF instead of COAP-based collision detection | PROX reconstruction · PROX quantitative dataset | Penetration: 100.17 -> 46.84 | Helped |
| use ground-truth scene SDF instead of COAP-based collision detection | PROX reconstruction · PROX quantitative dataset | V2V [mm]: 154.15 -> 154.01 | Helped |
| use ground-truth scene SDF instead of COAP-based collision detection | PROX reconstruction · PROX quantitative dataset | PJE [mm]: 154.34 -> 154.13 | Helped |
Closest papers by meaning
- Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021 · similarity 0.91)
- LEAP: Learning Articulated Occupancy of People (CVPR 2021 · similarity 0.91)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.87)
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021 · similarity 0.87)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.87)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · 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.