Research map / 3D vision / Human pose estimation
HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning
Eugene Valassakis, Guillermo Garcia-Hernando
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 |
|---|---|---|---|
| back-propagate camera-space loss through differentiable global positioning (add DGP training) (ablation) | HandDGP · HO3D-v2 | CS-MVE (mm): 85.4 -> 50.3 | Improved |
| add input image rectification to a canonical camera (ablation) | HandDGP without DGP · HO3D-v2 | CS-MVE (mm): 121.6 -> 85.4 | Improved |
| add image rectification to DGP (ablation) | HandDGP · FreiHAND | RS-MVE (mm): 6.9 -> 7.6 | Hurt |
| add image rectification to DGP (ablation) | HandDGP · FreiHAND | CS-MVE (mm): 49.4 -> 46.3 | Improved |
| learn keypoint confidence weights instead of fixing to 1.0 (ablation) | HandDGP · Human3.6M | CS-MVE (mm): 174.0 -> 162.0 | Improved |
| learn keypoint confidence weights instead of fixing to 1.0 (ablation) | HandDGP · HO3D-v2 | CS-MVE (mm): 50.4 -> 50.3 | No clear effect |
| use learned RootNet or root regression instead of geometric root finding | baseline root-relative model · FreiHAND | CS-MVE (mm): 50.0 -> 62.5 (RootNet), 81.8 (root regression) | Hurt |
| use DLT at test time versus PnP or optimization | baseline · FreiHAND | CS-MVE (mm): 50.0 vs 50.2 (PnP) vs 50.3 (Optimization) | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- HandOccNet — HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network (CVPR 2022) · better on 1 of 1 shared result
- I2L-MeshNet — I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image (ECCV 2020) · 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
- Dual Grid Net: Hand Mesh Vertex Regression from Single Depth Maps (ECCV 2020 · similarity 0.89)
- Neural Voting Field for Camera-Space 3D Hand Pose Estimation (CVPR 2023 · similarity 0.87)
- GEARS: Local Geometry-aware Hand-object Interaction Synthesis (CVPR 2024 · similarity 0.87)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.86)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.86)
- HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud (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.
