Research map / 3D vision / Human pose estimation
Full-Body Articulated Human-Object Interaction
Nan Jiang, Tengyu Liu, Zhexuan Cao, Jieming Cui, Zhiyuan Zhang, Yixin Chen, He Wang, Yixin Zhu, Siyuan Huang
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 |
|---|---|---|---|
| add interaction prior (cVAE) to pose optimization (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | chamfer distance: 87.90 -> 72.30 | Improved |
| add interaction prior to pose optimization (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | IoU: 18.81 -> 21.57 | Improved |
| add interaction prior to pose optimization (ablation) | Ours (no object knowledge) · CHAIRS test (w/o opt, no object knowledge) | chamfer distance: 165.3 -> 160.2 | Improved |
| add interaction prior to pose optimization (ablation) | Ours (no object knowledge) · CHAIRS test (w/o opt, no object knowledge) | contact: 3.295 -> 2.720 | Improved |
| add interaction prior to pose optimization (ablation) | Ours (no object knowledge) · CHAIRS test (w/o opt, no object knowledge) | penetration: 4.377 -> 4.530 | Hurt |
| add contrastive loss to prior training (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | chamfer distance: 87.28 -> 72.30 | Improved |
| add contrastive loss to prior training (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | contact: 2.393 -> 1.562 | Improved |
| add interaction awareness (concatenate human voxels) (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | chamfer distance: 78.12 -> 72.30 | Improved |
| add interaction awareness (concatenate human voxels) (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | rotation error: 17.88 -> 19.35 | Hurt |
| add interaction awareness (concatenate human voxels) (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | penetration: 1.022 -> 1.143 | Hurt |
| replace PARE human pose with ground-truth human pose (ablation) | Ours (w/ opt.) · CHAIRS test (w/ opt, known object structure) | chamfer distance: 72.30 -> 65.50 | Improved |
| use PARE human pose instead of none (no prior baseline) (ablation) | Ours · CHAIRS test (w/ opt, known object structure) | chamfer distance: 87.90 -> 73.79 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- LASR — LASR: Learning Articulated Shape Reconstruction From a Monocular Video (CVPR 2021) · better on 1 of 1 shared result
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
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.92)
- ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation (CVPR 2025 · similarity 0.90)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.89)
- Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions (CVPR 2025 · similarity 0.89)
- HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment (CVPR 2024 · similarity 0.89)
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos (NeurIPS 2026 · similarity 0.89)
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.
