Research map / 3D vision / Human pose estimation
Implicit 3D Human Mesh Recovery Using Consistency With Pose and Shape From Unseen-View
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 |
|---|---|---|---|
| Use ImpHMR instead of PARE | Frame-based human mesh recovery · 3DPW test | PA-MPJPE (mm): 52.3 -> 49.8 | Helped |
| Use ImpHMR instead of PARE | Human mesh recovery · 3DPW-OCC | MPJPE (mm): 90.5 -> 86.5 | Helped |
| Add feature fields and volume rendering to the HMR architecture (ablation) | ImpHMR · 3DPW | MPJPE (mm): 101.6 -> 96.5 | Helped |
| Add arbitrary-view imagination loss (ablation) | ImpHMR without geometric guidance · 3DPW | MPJPE (mm): 96.5 -> 94.9 | Helped |
| Add appearance consistency loss (ablation) | ImpHMR without geometric guidance · 3DPW | MPJPE (mm): 94.9 -> 93.5 | Helped |
| Add geometric guidance branch (ablation) | ImpHMR with regression, imagination, and consistency losses · 3DPW | MPJPE (mm): 93.5 -> 92.7 | Helped |
| Add foreground attention (ablation) | ImpHMR with DWConv aggregation · 3DPW | MPJPE (mm): 94.7 -> 92.7 | Helped |
| Use DWConv aggregation instead of GAP (ablation) | ImpHMR with foreground attention · 3DPW | MPJPE (mm): 95.3 -> 92.7 | Helped |
| Replace DWConv aggregation with convolution (ablation) | ImpHMR with foreground attention · 3DPW | MPJPE (mm): 92.7 -> 96.0 | Hurt |
| Add appearance consistency loss (ablation) | ImpHMR trained on COCO · LSP dataset | ESV (shape-view variation): 0.0774 -> 0.0561 | Helped |
| Use ImpHMR instead of PARE | Human mesh recovery · 3DPW | fps: 27.5 -> 88.8 | Helped |
Closest papers by meaning
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.88)
- GenHMR: Generative Human Mesh Recovery (AAAI 2025 · similarity 0.87)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.87)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.87)
- MEGA: Masked Generative Autoencoder for Human Mesh Recovery (CVPR 2025 · similarity 0.86)
- 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.