Load Balanced GANs for Multi-view Face Image Synthesis
This work addresses the challenge of generating realistic multi-view face images for applications like computer vision and graphics, but it is incremental as it builds on existing GAN-based methods with specific refinements.
The paper tackles the problem of multi-view face synthesis from a single image, which often suffers from appearance distortion, by proposing Load Balanced GANs (LB-GAN) to rotate face images to specified yaw angles, resulting in improved visual realism and identity preservation as demonstrated in experiments.
Multi-view face synthesis from a single image is an ill-posed problem and often suffers from serious appearance distortion. Producing photo-realistic and identity preserving multi-view results is still a not well defined synthesis problem. This paper proposes Load Balanced Generative Adversarial Networks (LB-GAN) to precisely rotate the yaw angle of an input face image to any specified angle. LB-GAN decomposes the challenging synthesis problem into two well constrained subtasks that correspond to a face normalizer and a face editor respectively. The normalizer first frontalizes an input image, and then the editor rotates the frontalized image to a desired pose guided by a remote code. In order to generate photo-realistic local details, the normalizer and the editor are trained in a two-stage manner and regulated by a conditional self-cycle loss and an attention based L2 loss. Exhaustive experiments on controlled and uncontrolled environments demonstrate that the proposed method not only improves the visual realism of multi-view synthetic images, but also preserves identity information well.