REVIEW 6 cited by
Generating Datasets of 3D Garments with Sewing Patterns
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Garments are ubiquitous in both real and many of the virtual worlds. They are highly deformable objects, exhibit an immense variety of designs and shapes, and yet, most garments are created from a set of regularly shaped flat pieces. Exploration of garment structure presents a peculiar case for an object structure estimation task and might prove useful for downstream tasks of neural 3D garment modeling and reconstruction by providing strong prior on garment shapes. To facilitate research in these directions, we propose a method for generating large synthetic datasets of 3D garment designs and their sewing patterns. Our method consists of a flexible description structure for specifying parametric sewing pattern templates and the automatic generation pipeline to produce garment 3D models with little-to-none manual intervention. To add realism, the pipeline additionally creates corrupted versions of the final meshes that imitate artifacts of 3D scanning. With this pipeline, we created the first large-scale synthetic dataset of 3D garment models with their sewing patterns. The dataset contains more than 20000 garment design variations produced from 19 different base types. Seven of these garment types are specifically designed to target evaluation of the generalization across garment sewing pattern topologies.
Forward citations
Cited by 6 Pith papers
-
ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
ClothTransformer is a unified latent-space Transformer for cloth simulation that handles body-driven garments, robotic manipulation, and free-fall collisions in one model with 4-9x lower error than prior methods and m...
-
InverseDraping: Recovering Sewing Patterns from 3D Garment Surfaces via BoxMesh Bridging
A two-stage autoregressive framework centered on BoxMesh recovers parametric sewing patterns from 3D garment surfaces, claiming state-of-the-art results on benchmarks and generalization to real scans and single-view images.
-
NGL: Natural Garment Language for Training-Free Sewing Pattern Estimation
NGL is a new structured language for garments that lets pre-trained vision-language models extract specifications from images and convert them deterministically into sewing patterns without any task-specific training.
-
ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction
ReWeaver reconstructs topology-accurate 3D garments and sewing patterns from sparse multi-view images by predicting seams and panels in 2D UV and 3D space using a new 100k-sample synthetic dataset.
-
ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
A single latent-space Transformer simulates body-driven garments, robotic cloth manipulation, and free-fall collisions with roughly 4–9× lower error than prior neural cloth methods.
-
ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
A unified latent-space Transformer achieves 4–9× lower vertex error than adapted baselines on three cloth-simulation scenarios and keeps temporal cost independent of mesh resolution.
Discussion (0). Sign in to comment.