Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
This addresses the challenge of high-quality image generation from diverse datasets for applications in computer vision, though it appears incremental as it builds on existing multi-source techniques.
The paper tackled the problem of generating new images from misaligned source images by modeling multiple variations like view angles and poses in a unified framework, achieving better performance than state-of-the-art methods as demonstrated by qualitative and quantitative results.
Generating new images with desired properties (e.g. new view/poses) from source images has been enthusiastically pursued recently, due to its wide range of potential applications. One way to ensure high-quality generation is to use multiple sources with complementary information such as different views of the same object. However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques. Therefore, we propose a new general approach which models multiple types of variations among sources, such as view angles, poses, facial expressions, in a unified framework, so that it can be employed on datasets of vastly different nature. We verify our approach on a variety of data including humans bodies, faces, city scenes and 3D objects. Both the qualitative and quantitative results demonstrate the better performance of our method than the state of the art.