Coordinate-based Texture Inpainting for Pose-Guided Image Generation
This addresses the challenge of realistic human image resynthesis for applications like garment transfer and face editing, though it is incremental as it builds on existing pose-guided methods.
The paper tackles the problem of pose-guided human image generation by completing the full body texture from a single photograph using a novel inpainting method that estimates source locations and warps correspondences, achieving state-of-the-art results in image synthesis.
We present a new deep learning approach to pose-guided resynthesis of human photographs. At the heart of the new approach is the estimation of the complete body surface texture based on a single photograph. Since the input photograph always observes only a part of the surface, we suggest a new inpainting method that completes the texture of the human body. Rather than working directly with colors of texture elements, the inpainting network estimates an appropriate source location in the input image for each element of the body surface. This correspondence field between the input image and the texture is then further warped into the target image coordinate frame based on the desired pose, effectively establishing the correspondence between the source and the target view even when the pose change is drastic. The final convolutional network then uses the established correspondence and all other available information to synthesize the output image. A fully-convolutional architecture with deformable skip connections guided by the estimated correspondence field is used. We show state-of-the-art result for pose-guided image synthesis. Additionally, we demonstrate the performance of our system for garment transfer and pose-guided face resynthesis.