Unsupervised Pose Flow Learning for Pose Guided Synthesis
This addresses the challenge of preserving appearance details in image synthesis for arbitrary poses, which is important for applications in fashion and virtual try-on, though it appears incremental by building on existing pose-guided synthesis approaches.
The paper tackles the problem of pose guided synthesis by proposing an unsupervised pose flow learning scheme to transfer appearance details from a source image to a target pose, with experiments showing favorable comparisons to state-of-the-art methods on datasets like DeepFashion and MVC.
Pose guided synthesis aims to generate a new image in an arbitrary target pose while preserving the appearance details from the source image. Existing approaches rely on either hard-coded spatial transformations or 3D body modeling. They often overlook complex non-rigid pose deformation or unmatched occluded regions, thus fail to effectively preserve appearance information. In this paper, we propose an unsupervised pose flow learning scheme that learns to transfer the appearance details from the source image. Based on such learned pose flow, we proposed GarmentNet and SynthesisNet, both of which use multi-scale feature-domain alignment for coarse-to-fine synthesis. Experiments on the DeepFashion, MVC dataset and additional real-world datasets demonstrate that our approach compares favorably with the state-of-the-art methods and generalizes to unseen poses and clothing styles.