SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing
This work addresses the need for size-sensitive 3D clothing modeling and editing in computer graphics and virtual try-on applications, representing an incremental advancement with new models and a dataset.
The paper tackles the problem of predicting 3D clothing deformation based on garment size and parsing clothing from input meshes, introducing SizerNet and ParserNet models that achieve better parsing accuracy and size prediction than baselines on the SIZER dataset.
While models of 3D clothing learned from real data exist, no method can predict clothing deformation as a function of garment size. In this paper, we introduce SizerNet to predict 3D clothing conditioned on human body shape and garment size parameters, and ParserNet to infer garment meshes and shape under clothing with personal details in a single pass from an input mesh. SizerNet allows to estimate and visualize the dressing effect of a garment in various sizes, and ParserNet allows to edit clothing of an input mesh directly, removing the need for scan segmentation, which is a challenging problem in itself. To learn these models, we introduce the SIZER dataset of clothing size variation which includes $100$ different subjects wearing casual clothing items in various sizes, totaling to approximately 2000 scans. This dataset includes the scans, registrations to the SMPL model, scans segmented in clothing parts, garment category and size labels. Our experiments show better parsing accuracy and size prediction than baseline methods trained on SIZER. The code, model and dataset will be released for research purposes.