Research map / 3D vision / Human pose estimation
Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Adapt HOI images to hand-only images using GAN and mesh-renderer guidance, without HOI 3D pose labels | 3D hand pose estimation · Dexter-Object | 3D PCK | Helped |
| Adapt HOI images to hand-only images using GAN and mesh-renderer guidance, without HOI 3D pose labels | 3D hand pose estimation · Ego-Dexter | 3D PCK | Helped |
| Adapt HOI images to hand-only images using GAN and mesh-renderer guidance, without HOI 3D pose labels | 3D hand pose estimation · HO3D EXTRAP | error rate: 28.24 vs 24.74 | Mixed |
| Adapt HOI images to hand-only images using GAN and mesh-renderer guidance, without HOI 3D pose labels | 3D hand pose estimation · HO3D OBJECT | error rate: 25.93 vs 18.39 | Mixed |
| Use HO3D 3D skeleton annotations during training | Proposed method · HO3D | error rate: 28.24 -> 23.63; 25.93 -> 20.59 | Helped |
| Add test-time iterative refinement of the MANO parameter using 2D joint consistency (ablation) | Proposed method · Dexter-Object and Ego-Dexter | average hand pose estimation accuracy: 4.3%; 6.5% | Helped |
| Add GAN-based image adaptation after initial mesh-rendered reconstruction (ablation) | Proposed method · Dexter-Object and Ego-Dexter | 3D PCK | Helped |
| Add mesh-renderer guidance to GAN image adaptation (ablation) | Proposed method · HOI hand-pose estimation | pose estimation accuracy | Helped |
Closest papers by meaning
- Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural Rendering (CVPR 2019 · similarity 0.91)
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.91)
- Crossing Nets: Combining GANs and VAEs With a Shared Latent Space for Hand Pose Estimation (CVPR 2017 · similarity 0.91)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.89)
- HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields (CVPR 2024 · similarity 0.89)
- SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation (AAAI 2024 · similarity 0.88)
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.