Identity-guided Face Generation with Multi-modal Contour Conditions
This work addresses identity preservation in face generation for applications like image restoration and editing, though it is incremental as it builds on existing StyleGAN methods.
The paper tackles the problem of identity ambiguity in face generation from vague contour conditions like low-resolution images or sketches by proposing a novel framework that uses an extra identity image and multi-modal contours to guide synthesis, achieving photo-realistic results at 1024x1024 resolution.
Recent face generation methods have tried to synthesize faces based on the given contour condition, like a low-resolution image or sketch. However, the problem of identity ambiguity remains unsolved, which usually occurs when the contour is too vague to provide reliable identity information (e.g., when its resolution is extremely low). Thus feasible solutions of image restoration could be infinite. In this work, we propose a novel framework that takes the contour and an extra image specifying the identity as the inputs, where the contour can be of various modalities, including the low-resolution image, sketch, and semantic label map. Concretely, we propose a novel dual-encoder architecture, in which an identity encoder extracts the identity-related feature, accompanied by a main encoder to obtain the rough contour information and further fuse all the information together. The encoder output is iteratively fed into a pre-trained StyleGAN generator until getting a satisfying result. To the best of our knowledge, this is the first work that achieves identity-guided face generation conditioned on multi-modal contour images. Moreover, our method can produce photo-realistic results with 1024$\times$1024 resolution.