Research map / 3D vision / Face and shape
Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh Deformation
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 |
|---|---|---|---|
| Refine the initial HMR mesh with joint and anchor deformation | HMR · WILD | sil IoU: 67.6 -> 76.5 | Helped |
| Refine the initial HMR mesh with joint and anchor deformation | HMR · RECON | sil IoU: 74.3 -> 85.0 | Helped |
| Refine the initial HMR mesh with joint and anchor deformation | HMR · SYN | sil IoU: 71.7 -> 79.6 | Helped |
| Add ground-truth silhouette input | HMD · WILD | sil IoU: 76.5 -> 82.4 | Helped |
| Add ground-truth silhouette input | HMD · RECON | sil IoU: 85.0 -> 88.3 | Helped |
| Add ground-truth silhouette input | HMD · SYN | sil IoU: 79.6 -> 85.7 | Helped |
| Add window-cropped input instead of full-image input for joint deformation (ablation) | HMD joint deformation · WILD | sil IoU: 68.3 -> 70.7 | Helped |
| Add window-cropped input instead of full-image input for anchor deformation (ablation) | HMD anchor deformation · WILD | sil IoU: 70.1 -> 71.3 | Helped |
| Combine joint and anchor deformation (ablation) | HMD · WILD | sil IoU: 71.3 -> 76.5 | Helped |
| Add vertex-level deformation to the anchor-deformed mesh (ablation) | HMD · RECON | 3D err full: 44.60 -> 44.10 | Helped |
| Add vertex-level deformation to the anchor-deformed mesh (ablation) | HMD · RECON | 3D err vis: 39.73 -> 41.76 | Hurt |
| Add vertex-level deformation to the anchor-deformed mesh (ablation) | HMD · SYN | 3D err full: 47.18 -> 44.75 | Helped |
Closest papers by meaning
- End-to-End Recovery of Human Shape and Pose (CVPR 2018 · similarity 0.91)
- Accurate 3D Body Shape Regression Using Metric and Semantic Attributes (CVPR 2022 · similarity 0.90)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.87)
- ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation (AAAI 2024 · similarity 0.87)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.86)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (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.