Research map / 3D vision / Human pose estimation
Neural Descent for Visual 3D Human Pose and Shape
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 |
|---|---|---|---|
| add fully supervised training to self-supervised HUND | HUND (SS) · 3DPW test set | MPJPE (mm): 90.4 -> 81.4 | Helped |
| add fully supervised training to self-supervised HUND | HUND (SS) · 3DPW test set | MPJPE-PA (mm): 63.5 -> 57.5 | Helped |
| use the last-stage meta-loss rather than the sum loss (ablation) | HUND (FS) · H3.6M P1 | MPJPE (mm): 83.26 -> 80.16 | Helped |
| use the minimum-over-stages meta-loss rather than the last-stage loss (ablation) | HUND (FS) · H3.6M P1 | MPJPE (mm): 80.16 -> 122.60 | Hurt |
| use the observable-improvement meta-loss rather than the last-stage loss (ablation) | HUND (FS) · H3.6M P1 | MPJPE (mm): 80.16 -> 123.90 | Hurt |
| use the maximum-over-stages meta-loss rather than the last-stage loss (ablation) | HUND (FS) · H3.6M P1 | MPJPE (mm): 80.16 -> 128.0 | Hurt |
| sum losses across stages rather than using the last-stage loss (ablation) | HUND (FS) · H3.6M P1 | MPJPE (mm): 80.16 vs 83.26 | No clear effect |
Closest papers by meaning
- Learning to Estimate 3D Human Pose and Shape From a Single Color Image (CVPR 2018 · similarity 0.89)
- End-to-End Recovery of Human Shape and Pose (CVPR 2018 · similarity 0.89)
- Convolutional Mesh Regression for Single-Image Human Shape Reconstruction (CVPR 2019 · similarity 0.88)
- 3D Human Pose Estimation From a Single Image via Distance Matrix Regression (CVPR 2017 · similarity 0.88)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.87)
- PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF (AAAI 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.