Identity-guided Face Generation with Multi-modal Contour Conditions

TL;DR

This paper introduces a novel identity-guided face generation framework that utilizes multi-modal contour conditions and an identity image, enabling high-resolution, photo-realistic face synthesis even with vague contours.

Contribution

It presents the first multi-modal contour conditioned face generation method guided by an identity image, using a dual-encoder architecture and iterative StyleGAN synthesis.

Findings

Produces 1024x1024 high-resolution realistic faces.

Handles various contour modalities including low-res images, sketches, and semantic maps.

First to achieve identity-guided face generation with multi-modal contours.

Abstract

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.