Research map / 3D vision / Human pose estimation
Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations
Nadine Rueegg, Christoph Lassner, Michael Black, Konrad Schindler, Nadine Rueegg, Christoph Lassner, Michael Black, Konrad Schindler
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 |
|---|---|---|---|
| Use chained representation cycling to learn from unpaired, unannotated images | 3D human pose and shape estimation on SURREAL · SURREAL | t-RMSE: 85.0 -> 204.0 | Hurt |
| Add 0.2% labeled segment data (ablation) | Chained representation cycling · SURREAL | 14seg IoU: 0.364 -> 0.488 | Improved |
| Add 0.5% labeled segment data (ablation) | Chained representation cycling · SURREAL | 14seg IoU: 0.364 -> 0.563 | Improved |
| Add 1% labeled segment data (ablation) | Chained representation cycling · SURREAL | 14seg IoU: 0.364 -> 0.622 | Improved |
| Add 100% labeled segment data (ablation) | Chained representation cycling · SURREAL | 14seg IoU: 0.364 -> 0.688 | Improved |
| Add 1% supervision (ablation) | Unsupervised 3D fitting · SURREAL | t-RMSE | Improved |
| Use a chained architecture rather than direct fully supervised training | 3D human pose estimation · SURREAL | MPJPE: 40.8 -> 69.5 | Hurt |
Closest papers by meaning
- Self-Supervised Neural Articulated Shape and Appearance Models (CVPR 2022 · similarity 0.88)
- Convolutional Mesh Regression for Single-Image Human Shape Reconstruction (CVPR 2019 · similarity 0.87)
- Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens (ICLR 2023 · similarity 0.87)
- Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation From Monocular Video (CVPR 2022 · similarity 0.87)
- Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop (ICCV 2019 · similarity 0.87)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · 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.
