RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesis

arXiv:2310.16074v2 Announce Type: replace
Abstract: Pose-guided person image synthesis task requires re-rendering a reference image, which should have a photorealistic appearance and flawless pose transfer. Since person images are highly structured, existing approaches require dense connections for complex deformations and occlusions because these are generally handled through multi-level warping and masking in latent space. The feature maps generated by convolutional neural networks do not have equivariance, and hence multi-level warping is required to perform pose alignment. Inspired by the ability …

abstract alignment arxiv cs.cv gradient guidance image images person photorealistic reference rendering synthesis through transfer type