Research map / 3D vision / Human pose estimation
Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction
Read the paperCheck 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 point-guided feature sampling to the no-sampling, no-masking model (ablation) | PointHMR · Human3.6M P2 | MPJPE: 63.2 -> 50.9 | Helped |
| Add point-guided feature sampling to the no-sampling, no-masking model (ablation) | PointHMR · Human3.6M P2 | PA-MPJPE: 39.9 -> 33.3 | Helped |
| Add progressive attention masking to point-guided sampling (ablation) | PointHMR · Human3.6M P2 | MPJPE: 50.9 -> 48.3 | Helped |
| Add progressive attention masking to point-guided sampling (ablation) | PointHMR · Human3.6M P2 | PA-MPJPE: 33.3 -> 32.9 | Helped |
| Replace no attention masking with single attention masking (M=1) (ablation) | PointHMR with point-guided sampling · Human3.6M P2 | MPJPE: 50.9 -> 49.1 | Helped |
| Replace no attention masking with single attention masking (M=1) (ablation) | PointHMR with point-guided sampling · Human3.6M P2 | PA-MPJPE: 33.3 -> 33.5 | Hurt |
| Replace single attention masking with progressive attention masking (ablation) | PointHMR with point-guided sampling · Human3.6M P2 | MPJPE: 49.1 -> 48.3 | Helped |
| Replace single attention masking with progressive attention masking (ablation) | PointHMR with point-guided sampling · Human3.6M P2 | PA-MPJPE: 33.5 -> 32.9 | Helped |
| Use point-guided sampling and progressive masking instead of neither component (ablation) | PointHMR · Human3.6M P2 | MPJPE: 63.2 -> 48.3 | Helped |
| Use point-guided sampling and progressive masking instead of neither component (ablation) | PointHMR · Human3.6M P2 | PA-MPJPE: 39.9 -> 32.9 | Helped |
Closest papers by meaning
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.88)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.87)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.87)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.87)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.87)
- BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025 · similarity 0.86)
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.