Research map / 3D vision / Human pose estimation
Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation
Taosha Fan, Kalyan Vasudev Alwala, Donglai Xiang, Weipeng Xu, Todd Murphey, Mustafa Mukadam
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 sparse constrained formulation instead of dense unconstrained optimization | SMPL pose and shape optimization · Human3.6M | optimization time (s): 20 -> 0.004 | Improved |
| use sparse constrained formulation in place of dense one (ablation) | Gauss-Newton direction, SMPL and SMPL+H · CPU time Experiments 1-3 | CPU time | Improved |
| increase number of measurements N from 120 to 600 (ablation) | sparse constrained method · SMPL / SMPL+H CPU time | speedup | Improved |
| use SMPL+H (51 joints) instead of SMPL (23 joints) (ablation) | sparse constrained method · SMPL / SMPL+H CPU time | speedup: CPU time ratio 4.49 -> 1 | Improved |
| increase number of shape parameters P from 0 to 10 (ablation) | sparse constrained method · SMPL / SMPL+H CPU time | speedup | Hurt |
| use SCOPE instead of regression method SPIN | Human3.6M Protocol 1 · Human3.6M Protocol 1 | MPJPE (mm): 65.6 -> 61.5 | Improved |
| use SCOPE instead of regression method SPIN | Human3.6M Protocol 1 · Human3.6M Protocol 1 | PA-MPJPE (mm): 44.6 -> 48.2 | Hurt |
| use SCOPE instead of SPIN | MPI-INF-3DHP rigid aligned · MPI-INF-3DHP (rigid aligned) | MPJPE (mm): 67.5 -> 62.1 | Improved |
| use SCOPE instead of SPIN | 3DPW · 3DPW | MPJPE (mm): 96.9 -> 98.6 | Hurt |
| use SCOPE instead of XNect optimization | 3DPW · 3DPW | MPJPE (mm): 134.2 -> 98.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- SPIN — SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition (AAAI 2021) · better on 4 of 9 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
- Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach (TPAMI 2016 · similarity 0.89)
- Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop (ICCV 2019 · similarity 0.89)
- Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms (NeurIPS 2022 · similarity 0.89)
- Robust 3D Human Pose Estimation from Single Images or Video Sequences (TPAMI 2018 · similarity 0.89)
- Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation From Monocular Video (CVPR 2022 · similarity 0.89)
- Probabilistic 3D Human Shape and Pose Estimation From Multiple Unconstrained Images in the Wild (CVPR 2021 · similarity 0.89)
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.
