Mask-Guided Portrait Editing With Conditional GANs

Abstract

a) Mask2image (b) Component editing (c) Component transfer Figure 1: We propose a framework based on conditional GANs for mask-guided portrait editing. (a) Our framework can generate diverse and realistic faces using one input target mask (lower left corner in the first image). (b) Our framework allows us to edit the mask to change the shape of face components, i.e. mouth, eyes, hair. (c) Our framework also allows us to transfer the appearance of each component for a portrait, including hair color. AbstractPortrait editing is a popular subject in photo manipulation. The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in existing techniques: diversity, quality, and controllability for portrait synthesis and editing. To address these issues, we propose a novel end-to-end learning framework that leverages conditional GANs guided by provided face masks for generating faces. The framework learns feature embeddings for every face component (e.g., mouth, hair, eye), separately, contributing to better correspondences for image translation, and local face editing. With the mask, our network is available to many applications, like face synthesis driven by mask, face Swap+ (including hair in swapping), and local manipulation. It can also boost the performance of face parsing a bit as an option of data augmentation.

SEAN: Image Synthesis With Semantic Region-Adaptive Normalization

“…Since then, their method is extended by several following works to scenarios including: unsupervised learning [53,30], few-shot learning [31], high resolution image synthesis [44], multimodal image synthesis [54,21] and multi-domain image synthesis [9]. Among various image-to-image translation problems, semantic image synthesis is a particularly useful genre as it enables easy user control by modifying the input semantic layout image [28,5,15,38]. To date, the SPADE [38] [20,27]).…”

A State-of-the-Art Review on Image Synthesis With Generative Adversarial Networks

“…Gu et al [84] proposed a portrait editing framework based on mask-guided conditional GANs, and it uses the face masks to guide the image generation. Its framework is shown in Fig.…”

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

“…For the first task, to enforce the existence of important facial features in the generated drawing, besides a discriminator D that analyzes the full drawing, we add three local discriminators D ln , D le , D ll to focus on discriminating the nose drawing, eye drawing and lip drawing respectively. The inputs to these local discriminators are masked drawings, where masks are obtained from a face parsing network [6].…”