Presentation

<
Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics
SessionTailor Made
DescriptionWe introduce Dress-1-to-3 to reconstruct physics-plausible, simulation-ready separated garments from an in-the-wild image. Starting with the image, our approach combines a pre-trained image-to-sewing pattern generation model with a pre-trained multi-view diffusion model. The sewing pattern is refined using a differentiable garment simulator based on the generated multi-view images.
Authors
Xuan Li
University of California Los Angeles
Chang Yu
University of California Los Angeles
Wenxin Du
University of California Los Angeles
Ying Jiang
University of California Los Angeles
Tianyi Xie
University of California Los Angeles
Yunuo Chen
University of California Los Angeles
Yin Yang
University of Utah
Chenfanfu Jiang
University of California Los Angeles
Event Type
Technical Paper
TimeMonday, 11 August 20254:25pm - 4:35pm PDT
LocationWest Building, Rooms 211-214
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Monday, 11 August 20253:45pm - 5:15pm PDTWest Building, Rooms 211-214
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationSingle View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
Similar Presentations
GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies
Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
Rags2Riches: Computational Garment Reuse