Research map / 3D vision / Human pose estimation
Nonrigid Object Contact Estimation With Regional Unwrapping Transformer
Wei Xie, Zimeng Zhao, Shiying Li, Binghui Zuo, Yangang Wang
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 contact attention modules instead of an MLP (ablation) | RUFormer · HMDO | Max penetration (mm): 11.62 -> 10.42 | Improved |
| add image patches as visual cues (ablation) | RUFormer · HMDO | Max penetration (mm): 12.57 -> 10.42 | Improved |
| use proposed deformation estimation block instead of Point Transformer (ablation) | RUFormer · HMDO | Max penetration (mm): 10.75 -> 10.42 | Improved |
| use 4x4 sampling grid instead of 8x8 (ablation) | RUFormer · HMDO | Max penetration (mm): 11.16 -> 10.42 | Improved |
| use 64x64 RUP instead of 32x32 (ablation) | RUFormer · HMDO | Max penetration (mm): 11.04 -> 10.42 | Improved |
| increase RUP size to 128x128 (ablation) | RUFormer · HMDO | intersection volume (cm^3): 8.64 vs 8.56 | No clear effect |
| apply contact optimization on hand-object pose estimates | Baseline pose network · HMDO | Max penetration (mm): 19.46 -> 10.42 | Improved |
| apply contact optimization on hand pose accuracy | Baseline pose network · HMDO | MPJPE hand (mm): 18.54 -> 18.97 | Hurt |
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.
- ContactOpt — ContactOpt: Optimizing Contact To Improve Grasps (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
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.88)
- Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation (ICCV 2023 · similarity 0.87)
- ContactPose: A Dataset of Grasps with Object Contact and Hand Pose (ECCV 2020 · similarity 0.87)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.85)
- Learning Dense Hand Contact Estimation from Imbalanced Data (NeurIPS 2025 · similarity 0.84)
- Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer (CVPR 2024 · similarity 0.84)
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.
