Research map / 3D vision / Face and shape
TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style
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 the high/low-frequency decomposition and narrow-bandwidth mixture instead of the joint MLP baseline | TailorNet · TailorNet split 2 (train styles, test poses) | mean per-vertex error (mm): 10.6 -> 10.2 | Helped |
| Use the high/low-frequency decomposition and narrow-bandwidth mixture instead of the joint MLP baseline | TailorNet · TailorNet split 3 (test styles, train poses) | mean per-vertex error (mm): 11.7 -> 11.4 | Helped |
| Use the high/low-frequency decomposition and narrow-bandwidth mixture instead of the joint MLP baseline | TailorNet · TailorNet split 4 (test styles, test poses) | mean per-vertex error (mm): 11.6 -> 11.4 | Helped |
| Use an MLP instead of a UV Decoder for pose-dependent deformation | Single style-shape model · Loose-fit style-shape pair | mean per-vertex error (mm): 15.9 -> 14.5 | Helped |
| Use an MLP instead of a Graph CNN for pose-dependent deformation | Single style-shape model · Loose-fit style-shape pair | mean per-vertex error (mm): 16.1 -> 14.5 | Helped |
| Use an MLP instead of a UV Decoder for pose-dependent deformation | Single style-shape model · Tight-fit style-shape pair | mean per-vertex error (mm): 11.4 -> 10.1 | Helped |
| Use an MLP instead of a Graph CNN for pose-dependent deformation | Single style-shape model · Tight-fit style-shape pair | mean per-vertex error (mm): 11.7 -> 10.1 | Helped |
| Remove the frequency decomposition and predict style-shape prototype displacements directly (ablation) | TailorNet mixture model · Clothing wrinkle-detail prediction | wrinkle detail retention | Hurt |
| Combine training examples across styles and shapes in a joint MLP | TailorNet joint baseline · Clothing deformation across styles and shapes | visual realism | Hurt |
Closest papers by meaning
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021 · similarity 0.92)
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · similarity 0.89)
- Garment Recovery with Shape and Deformation Priors (CVPR 2024 · similarity 0.89)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.89)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.89)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.88)
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.