Research map / 3D vision / Face and shape
ECON: Explicit Clothed Humans Optimized via Normal Integration
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 an SMPL-X depth prior and front-back silhouette consistency to BiNI (ablation) | BiNI · CAPE and Renderpeople | Depth RMSE and MAE: CAPE RMSE: 27.64 -> 13.43; MAE: 21.11 -> 10.29; Renderpeople RMSE: 20.61 -> 14.43; MAE: 16.07 -> 11.26 | Helped |
| Add an SMPL-X depth prior and front-back silhouette consistency to BiNI (ablation) | BiNI · CAPE and Renderpeople | Speed (FPS): 0.52 -> 0.69 | Helped |
| Condition IF-Nets on the SMPL-X body (ablation) | IF-Nets · CAPE OOD poses | Chamfer: 2.116 -> 1.401 | Helped |
| Condition IF-Nets on the SMPL-X body (ablation) | IF-Nets · CAPE OOD poses | P2S: 1.233 -> 1.353 | Hurt |
| Condition IF-Nets on the SMPL-X body (ablation) | IF-Nets · CAPE OOD poses | Normals: 0.075 -> 0.056 | Helped |
| Condition IF-Nets on the SMPL-X body (ablation) | IF-Nets · Renderpeople OOD outfits | Chamfer: 1.883 -> 1.477 | Helped |
| Condition IF-Nets on the SMPL-X body (ablation) | IF-Nets · Renderpeople OOD outfits | P2S: 1.622 -> 1.564 | Helped |
| Condition IF-Nets on the SMPL-X body (ablation) | IF-Nets · Renderpeople OOD outfits | Normals: 0.070 -> 0.055 | Helped |
| Add front-back silhouette consistency during normal integration (ablation) | d-BiNI · Front and back surface reconstruction | Blobby artifacts | Helped |
| Use ECON_EX instead of ICON on CAPE OOD poses | ECON_EX · CAPE OOD poses | Normals (L2): 0.0409 -> 0.0367 | Helped |
| Use ECON_EX instead of ICON on CAPE OOD poses | ECON_EX · CAPE OOD poses | P2S: 0.909 -> 0.917 | Mixed |
| Use ECON_EX instead of PaMIR on Renderpeople | ECON_EX · Renderpeople OOD outfits | Chamfer: 1.296 -> 1.342 | Hurt |
Closest papers by meaning
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.89)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.88)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.88)
- HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models (CVPR 2024 · similarity 0.88)
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.87)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · 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.