Research map / 3D vision / Face and shape
SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing
Garvita Tiwari, Bharat Lal Bhatnagar, Tony Tung, Gerard Pons-Moll
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Polo | per-vertex error (mm): 17.25 -> 14.33 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Shirt | per-vertex error (mm): 19.35 -> 14.56 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Vest | per-vertex error (mm): 18.56 -> 15.89 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Hoodies | per-vertex error (mm): 23.69 -> 15.76 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, T-Shirt | per-vertex error (mm): 15.98 -> 13.77 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Shorts | per-vertex error (mm): 20.12 -> 16.07 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Pants | per-vertex error (mm): 18.2 -> 17.24 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Coat | per-vertex error (mm): 22.19 -> 15.34 | Improved |
| predict sparse convex-combination weights over input vertices instead of direct displacement field | ParserNet · SIZER garment parsing, Shorts2 | per-vertex error (mm): 23.45 -> 16.23 | Improved |
| predict sparse convex-combination weights instead of a linear LASSO model | ParserNet · SIZER garment parsing, Polo | per-vertex error (mm): 32.21 -> 14.33 | Improved |
| use SizerNet instead of linear scaling plus alignment | SizerNet · SIZER garment resizing, Polo t-shirt | per-vertex error (mm): 35.05 -> 16.42 | Improved |
| use SizerNet instead of linear scaling plus alignment | SizerNet · SIZER garment resizing, Polo t-shirt | surface area error (%): 8.45 -> 1.79 | Improved |
Closest papers by meaning
- GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns (ECCV 2024 · similarity 0.91)
- Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images (ECCV 2020 · similarity 0.90)
- TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style (CVPR 2020 · similarity 0.90)
- Multi-Garment Net: Learning to Dress 3D People From Images (ICCV 2019 · similarity 0.90)
- 4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations (CVPR 2024 · similarity 0.88)
- Garment Recovery with Shape and Deformation Priors (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.
