Research map / 3D vision / Human pose estimation
Embodied Scene-aware Human Pose Estimation
Zhengyi Luo, Shun Iwase, Ye Yuan, Kris M. Kitani
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 embodied scene-aware estimation with MPG and physics simulation | Human pose estimation on PROX RGB · PROX | ACD: 171.7 vs 173.2 | Improved |
| Use modified scene geometry instead of the original scanned scene (ablation) | Embodied pose estimator · PROX RGB ablation | ACD: 252.1 -> 171.7 | Improved |
| Add voxel-based scene awareness (ablation) | Embodied pose estimator · PROX RGB ablation | ACD: 265.0 -> 171.7 | Improved |
| Use multiple MPG gradient steps rather than a single step (ablation) | Embodied pose estimator · PROX RGB ablation | ACD: 326.9 -> 171.7 | Improved |
| Add the geometric translation step to the MPG transform (ablation) | Embodied pose estimator · PROX RGB ablation | ACD: 604.6 -> 171.7 | Improved |
| Add the TCN to the MPG transform (ablation) | Embodied pose estimator · PROX RGB ablation | ACD: 223.2 -> 171.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- HuMoR — HuMoR: 3D Human Motion Model for Robust Pose Estimation (ICCV 2021) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI (CVPR 2024 · similarity 0.88)
- Human-Aware Object Placement for Visual Environment Reconstruction (CVPR 2022 · similarity 0.88)
- Generating 3D People in Scenes Without People (CVPR 2020 · similarity 0.88)
- Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning (CVPR 2025 · similarity 0.87)
- Pose Priors from Language Models (CVPR 2025 · similarity 0.87)
- Multimodal Sense-Informed Forecasting of 3D Human Motions (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.
