Research map / 3D vision / Face and shape
SiCloPe: Silhouette-Based Clothed People
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 |
|---|---|---|---|
| Use silhouette plus 2D pose rather than RGB plus 2D pose (ablation) | SiCloPe shape representation · Renderpeople dataset | 2D IoU: 0.826 -> 0.886 | Helped |
| Use silhouette plus 2D pose rather than RGB plus 2D pose (ablation) | SiCloPe shape representation · Renderpeople dataset | Chamfer Distance (CD): 1.66 -> 1.36 | Helped |
| Use silhouette-based shape representation instead of direct voxel prediction (ablation) | SiCloPe · Renderpeople dataset | 2D IoU: 0.471 -> 0.886 | Helped |
| Use silhouette-based shape representation instead of direct voxel prediction (ablation) | SiCloPe · Renderpeople dataset | Chamfer Distance (CD): 2.49 -> 1.36 | Helped |
| Add greedy view sampling instead of random view selection (ablation) | Deep visual hull · 12 inferred silhouettes | Chamfer Distance (CD): 1.41 -> 1.34 | Helped |
| Add greedy view sampling instead of random view selection (ablation) | Visual hull · 12 inferred silhouettes | Chamfer Distance (CD): 2.12 -> 1.37 | Helped |
| Use deep visual hull instead of conventional visual hull (ablation) | Optimized-view reconstruction · 12 inferred silhouettes | Earth Mover’s Distance (EMD): 6.93 -> 3.66 | Helped |
| Use deep visual hull instead of conventional visual hull (ablation) | Random-view reconstruction · 12 inferred silhouettes | Earth Mover’s Distance (EMD): 6.95 -> 3.79 | Helped |
Closest papers by meaning
- Learning to Dress 3D People in Generative Clothing (CVPR 2020 · similarity 0.91)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.89)
- Human Shape From Silhouettes Using Generative HKS Descriptors and Cross-Modal Neural Networks (CVPR 2017 · similarity 0.89)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.88)
- Design2Cloth: 3D Cloth Generation from 2D Masks (CVPR 2024 · similarity 0.87)
- HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models (CVPR 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.