Research map / 3D vision / Human pose estimation
Putting People in Their Place: Monocular Regression of 3D People in Depth
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 |
|---|---|---|---|
| introduce BEV's bird's-eye-view 3D representation | BEV · RH | PCDR^0.2 All (%): 54.83 -> 57.17 | Helped |
| add weakly supervised training (ablation) | BEV · RH | PCDR^0.2 All (%): 57.17 -> 68.27 | Helped |
| add the piece-wise depth layer loss (ablation) | BEV · RH | PCDR^0.2 All (%): 55.97 -> 68.27 | Helped |
| add the ambiguity-compatible age loss (ablation) | BEV · RH | PCDR^0.2 All (%): 61.47 -> 68.27 | Helped |
| add weakly supervised training (ablation) | BEV · AGORA test Kid subset | MVE: 146.0 -> 125.9 | Helped |
| add weakly supervised training (ablation) | BEV · AGORA test Kid subset | F1 score: 0.58 -> 0.55 | Hurt |
| add front-view conditioning for bird's-eye-view estimation (ablation) | BEV · AGORA | NMVE: 118.9 -> 108.3 | Helped |
| add the 3D Offset map (ablation) | BEV · RH | PCDR^0.2: 60.76 -> 68.27 | Helped |
| add the 3D Offset map (ablation) | BEV · AGORA | NMVE: 126.6 -> 108.3 | Helped |
| use piece-wise depth loss instead of ordinal depth loss (ablation) | BEV · AGORA validation | 3D translation Dist.: 0.608 -> 0.518 | Helped |
Closest papers by meaning
- Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints (CVPR 2018 · similarity 0.90)
- Unite the People: Closing the Loop Between 3D and 2D Human Representations (CVPR 2017 · similarity 0.88)
- Coherent Reconstruction of Multiple Humans From a Single Image (CVPR 2020 · similarity 0.88)
- Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks (CVPR 2021 · similarity 0.87)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · similarity 0.87)
- Reconstructing People, Places, and Cameras (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.