Research map / 3D vision / Human pose estimation
ContactOpt: Optimizing Contact To Improve Grasps
Patrick Grady, Chengcheng Tang, Christopher D. Twigg, Minh Vo, Samarth Brahmbhatt, Charles C. Kemp
Check 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 |
|---|---|---|---|
| Refine ContactPose poses to match ground-truth thermal contact | ContactOpt · ContactPose | Perceptual (%): 30.6 ± 3.8 -> 69.4 ± 3.8 | Improved |
| Refine ContactPose poses to match ground-truth thermal contact | ContactOpt · ContactPose | Contact Precision (%): 64.6 -> 75.9 | Improved |
| Refine ContactPose poses to match ground-truth thermal contact | ContactOpt · ContactPose | Intersection Volume (cm^3): 2.45 ± 1.99 -> 1.35 ± 0.90 | Improved |
| Optimize perturbed poses to match predicted target contact | ContactOpt · Perturbed ContactPose | MPJPE (mm): 79.89 -> 25.05 | Improved |
| Optimize perturbed poses to match predicted target contact | ContactOpt · Perturbed ContactPose | Intersection Volume (cm^3): 8.46 ± 16.49 -> 12.83 ± 8.00 | Hurt |
| Optimize perturbed poses to match predicted target contact | ContactOpt · Perturbed ContactPose | Contact Recall (%): 11.5 -> 54.8 | Improved |
| Refine image-based hand pose estimates using contact optimization | ContactOpt · HO-3D | MPJPE (mm): 57.7 -> 48.1 | Improved |
| Refine image-based hand pose estimates using contact optimization | ContactOpt · HO-3D | Perceptual (%): reference -> 85.2 ± 2.7 | Improved |
| Use 8 rather than 1 random initialization (ablation) | ContactOpt · HO-3D image-based pose estimates | MPJPE (mm): 53.6 -> 48.1 | Improved |
| Use 8 rather than 4 random initializations (ablation) | ContactOpt · HO-3D image-based pose estimates | MPJPE (mm): 51.2 -> 48.1 | Improved |
Later papers that compared with this method
5 later accepted papers report ContactOpt as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model (ECCV 2024 · better on 3 of 3 shared results)
- ContactGen: Generative Contact Modeling for Grasp Generation (ICCV 2023 · better on 1 of 1 shared result)
- Nonrigid Object Contact Estimation With Regional Unwrapping Transformer (ICCV 2023 · better on 1 of 1 shared result)
- S2Contact: Graph-Based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning (ECCV 2022 · better on 4 of 4 shared results)
- TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement (ECCV 2022 · better on 2 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
- ContactPose: A Dataset of Grasps with Object Contact and Hand Pose (ECCV 2020 · similarity 0.92)
- Grasp’D: Differentiable Contact-Rich Grasp Synthesis for Multi-Fingered Hands (ECCV 2022 · similarity 0.90)
- VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation (NeurIPS 2026 · similarity 0.88)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.88)
- MANUS: Markerless Grasp Capture using Articulated 3D Gaussians (CVPR 2024 · similarity 0.87)
- DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model (AAAI 2025 · 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.
