Research map / 3D vision / Human pose estimation
Unsupervised 3D Pose Transfer With Cross Consistency and Dual Reconstruction
Chaoyue Song, Jiacheng Wei, Ruibo Li, Fayao Liu, Guosheng Lin
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 ARAP deformer in the training loop (ablation) | X-DualNet · SMPL | PMD: 1.98 -> 1.67 | Improved |
| add ARAP deformer in the training loop (ablation) | X-DualNet · SMPL | CD: 3.37 -> 2.71 | Improved |
| add backward correspondence loss (ablation) | X-DualNet · SMPL | PMD: 1.84 -> 1.67 | Improved |
| add backward correspondence loss (ablation) | X-DualNet · SMPL | EMD: 6.35 -> 5.96 | Improved |
| use ElaIN instead of SPAdaIN (ablation) | 3D-CoreNet · SMPL | PMD: 1.01 -> 0.49 | Improved |
| use ElaIN instead of SPAdaIN (ablation) | 3D-CoreNet · SMPL | EMD: 4.66 -> 3.61 | Improved |
| use X-DualNet instead of unsupervised baseline | unsupervised baseline · SMAL | PMD: 16.50 -> 4.48 | Improved |
| use X-DualNet instead of unsupervised baseline | unsupervised baseline · SMPL | CD: 4.05 -> 2.71 | Improved |
| unsupervised X-DualNet vs supervised NPT | NPT · SMPL | PMD: 2.77 -> 1.67 | Improved |
| supervised 3D-CoreNet vs unsupervised X-DualNet | X-DualNet · SMPL | PMD: 1.67 -> 0.49 | Hurt |
Closest papers by meaning
- 3D Pose Transfer with Correspondence Learning and Mesh Refinement (NeurIPS 2021 · similarity 0.91)
- Unsupervised Shape and Pose Disentanglement for 3D Meshes (ECCV 2020 · similarity 0.89)
- Weakly-supervised 3D Pose Transfer with Keypoints (ICCV 2023 · similarity 0.89)
- Towards Robust 3D Pose Transfer with Adversarial Learning (CVPR 2024 · similarity 0.88)
- Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses (NeurIPS 2024 · similarity 0.87)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.85)
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.
