Research map / 3D vision / Face and shape
ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns
Ren Li, Benoît Guillard, Pascal Fua
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 |
|---|---|---|---|
| use ISP 2D implicit field instead of 3D UDF at resolution 128 | garment reconstruction · shirts train | Chamfer distance (x10^-4): 0.641 -> 0.454 | Improved |
| use ISP instead of UDF at resolution 512 | garment reconstruction · shirts test | Chamfer distance (x10^-4): 0.424 -> 0.349 | Improved |
| use ISP instead of UDF at resolution 256 | garment reconstruction · shirts test | normal consistency (%): 98.44 -> 98.83 | Improved |
| use ISP instead of UDF at resolution 256 | reconstruction time · shirts train | time (ms): 2379 -> 77 | Improved |
| use ISP instead of UDF at resolution 512 | reconstruction time · shirts train | time (ms): 13258 -> 261 | Improved |
| increase marching cubes resolution from 256 to 512 for ISP | ISP · shirts test | Chamfer distance (x10^-4): 0.392 -> 0.349 | Improved |
| increase marching cubes resolution from 256 to 512 for UDF | UDF · shirts train | normal consistency (%): 99.20 -> 98.77 | Hurt |
| increase marching cubes resolution from 256 to 512 for UDF | UDF · shirts test | normal consistency (%): 98.44 -> 98.09 | Hurt |
| use ISP instead of DrapeNet in human evaluation of draping | ISP · draping realism | participants preference (%): 25.00 -> 62.69 | Improved |
| use ISP draping model instead of DrapeNet | ISP · draping intersections | intersection ratio | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DrapeNet — DrapeNet: Garment Generation and Self-Supervised Draping (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns (ECCV 2024 · similarity 0.91)
- Reconstruction of Manipulated Garment with Guided Deformation Prior (NeurIPS 2024 · similarity 0.91)
- GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss (TPAMI 2020 · similarity 0.90)
- Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates (TPAMI 2026 · similarity 0.90)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · similarity 0.90)
- Garment Recovery with Shape and Deformation Priors (CVPR 2024 · similarity 0.89)
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.
