SwapNet: Image based Garment transfer
Amit Raj
Patsorn Sangkloy
Huiwen Chang
James Hays
Duygu Ceylan
Jingwan Lu
We present Swapnet,a framework totransfer garments across images of people with arbitrary body pose, shape, and clothing. Gar- ment transfer is a challenging task that requires (i) disentangling the features of the clothing from the body pose and shape and (ii) real- istic synthesis of the garment texture on the new body. We present a neural network architecture that tackles these sub-problems with two task-specific sub-networks. Since acquiring pairs of images showing the same clothing on different bodies is difficult, we propose a novel weakly- supervised approach that generates training pairs from a single image via data augmentation. We present the first fully automatic method for garment transfer in unconstrained images without solving the difficult 3D reconstruction problem. We demonstrate a variety of transfer results and highlight our advantages over traditional image-to-image and anal- ogy pipelines.
  title={SwapNet: Image based Garment transfer},
  author={Raj, Amit and Sangkloy, Patsorn and Chang, Huiwen and Hays, James and Ceylan, Duygu and Lu, Jingwan},
  journal={European Conference on Computer Vision, ECCV},
View Paper
Coming soon!!