Research map / 3D vision / Human pose estimation
"CHORE: Contact, Human and Object REconstruction from a Single RGB Image"
Xianghui Xie, Bharat Lal Bhatnagar, Gerard Pons-Moll
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 depth-aware scaling instead of direct perspective camera (ablation) | CHORE · BEHAVE | Object Chamfer (cm): 15.58 -> 10.66 | Improved |
| add depth-aware scaling instead of direct perspective camera (ablation) | CHORE · BEHAVE | SMPL Chamfer (cm): 7.63 -> 5.58 | Improved |
| use perspective depth-aware scaling instead of weak perspective camera (ablation) | CHORE · BEHAVE | Object Chamfer (cm): 25.24 -> 10.66 | Improved |
| add object rotation field f^R (ablation) | CHORE · BEHAVE | Object Chamfer (cm): 17.54 -> 10.66 | Improved |
| add object translation field f^c (ablation) | CHORE · BEHAVE | Object Chamfer (cm): 14.25 -> 10.66 | Improved |
| add contact term E^c_data (ablation) | CHORE · BEHAVE | Object Chamfer (cm): 10.86 -> 10.66 | Improved |
| add contact term E^c_data (ablation) | CHORE · BEHAVE | SMPL Chamfer (cm): 5.51 -> 5.58 | No clear effect |
| add joint model fitting to neural reconstruction (ablation) | CHORE · BEHAVE | Object Chamfer (cm): 15.34 -> 10.66 | Improved |
| add joint human-object reasoning to FrankMocap | FrankMocap · BEHAVE | human v2v (cm): 6.91 -> 5.46 | Improved |
| replace PHOSA with CHORE | PHOSA · BEHAVE | Object Chamfer (cm): 26.62 -> 10.66 | Improved |
| replace Weng et al. with CHORE | Weng et al. · BEHAVE-- (10 categories) | Object Chamfer (cm): 51.86 -> 13.15 | Improved |
Closest papers by meaning
- Reconstructing Humans and Objects in Interaction using Large Reconstruction Models (ECCV 2026 · similarity 0.90)
- Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation (CVPR 2024 · similarity 0.87)
- ContactField: Implicit Field Representation for Multi-Person Interaction Geometry (NeurIPS 2024 · similarity 0.87)
- Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer (CVPR 2024 · similarity 0.87)
- PICO: Reconstructing 3D People In Contact with Objects (CVPR 2025 · similarity 0.87)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.87)
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.
