Research map / 3D vision / Face and shape
Structure-Preserving 3D Garment Modeling with Neural Sewing Machines
Xipeng Chen, Guangrun Wang, Dizhong Zhu, Xiaodan Liang, Philip Torr, Liang Lin
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 sewing-pattern-guided NSM for single-view garment reconstruction | Single-view garment reconstruction · Single-view garment reconstruction | Chamfer (cm): 2.08 vs. 3.31 | Improved |
| Use sewing-pattern-guided NSM for single-view garment reconstruction | Single-view garment reconstruction · Single-view garment reconstruction | P2S (cm): 1.90 vs. 3.84 | Improved |
| Use sewing-pattern-guided NSM for single-view garment reconstruction | Single-view garment reconstruction · Single-view garment reconstruction | MGLE (cm): 3.73 vs. 3.42 | Mixed |
| Add inner-panel structure-preserving loss (ablation) | NSM with reconstruction loss · Garment reconstruction from sewing patterns, All | MGLE (cm): 4.38 -> 4.69 | Hurt |
| Add inner-panel structure-preserving loss (ablation) | NSM with reconstruction loss · Garment reconstruction from sewing patterns, All | Chamfer (cm): 1.81 -> 1.80 | No clear effect |
| Add inner-panel structure-preserving loss (ablation) | NSM with reconstruction loss · Garment reconstruction from sewing patterns, All | P2S (cm): 1.69 -> 1.76 | No clear effect |
| Add inter-panel structure-preserving loss (ablation) | NSM with reconstruction and inner-panel losses · Garment reconstruction from sewing patterns, All | MGLE (cm): 4.69 -> 3.62 | Improved |
| Add surface-normal loss (ablation) | NSM with reconstruction, inner-panel, and inter-panel losses · Garment reconstruction from sewing patterns, All | MGLE (cm): 3.62 -> 3.54 | Improved |
| Use basic-panel-group rather than panel-level encoding (ablation) | NSM sewing-pattern encoder · Garment reconstruction from sewing patterns, All | Chamfer (cm): 1.92 -> 1.65 | Improved |
| Use basic-panel-group rather than panel-level encoding (ablation) | NSM sewing-pattern encoder · Garment reconstruction from sewing patterns, All | P2S (cm): 1.78 -> 1.46 | Improved |
| Use a unified decoder instead of category-specific decoders (ablation) | NSM garment decoder · Garment reconstruction from sewing patterns, All | MGLE (cm): 4.36cm vs. 3.54cm | Improved |
| Use a unified decoder instead of category-specific decoders (ablation) | NSM garment decoder · Garment reconstruction from sewing patterns, All | Chamfer (cm): 1.63cm vs. 1.65cm | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- BCNet — BCNet: Learning Body and Cloth Shape from A Single Image (ECCV 2020) · better on 2 of 3 shared results
- Pixel2Mesh — Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (ECCV 2018) · better on 3 of 3 shared results
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
- Generating Datasets of 3D Garments with Sewing Patterns (NeurIPS 2021 · similarity 0.93)
- Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns (ECCV 2026 · similarity 0.93)
- DeepCloth: Neural Garment Representation for Shape and Style Editing (TPAMI 2022 · similarity 0.92)
- ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction (CVPR 2026 · similarity 0.91)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · similarity 0.91)
- Reconstruction of Manipulated Garment with Guided Deformation Prior (NeurIPS 2024 · similarity 0.90)
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.
