AttGAN: Facial Attribute Editing by Only Changing What You Want

TL;DR

AttGAN introduces a novel facial attribute editing framework that changes only desired attributes while preserving other facial details, using attribute classification constraints and reconstruction learning for high-quality, realistic results.

Contribution

The paper proposes AttGAN, a new approach that avoids attribute-independent latent constraints, improving attribute editing quality and enabling attribute intensity and style control.

Findings

Outperforms state-of-the-art methods on CelebA dataset

Preserves facial details effectively during editing

Supports attribute intensity and style manipulation

Abstract

Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results. Based on the encoder-decoder architecture, facial attribute editing is achieved by decoding the latent representation of the given face conditioned on the desired attributes. Some existing methods attempt to establish an attribute-independent latent representation for further attribute editing. However, such attribute-independent constraint on the latent representation is excessive because it restricts the capacity of the latent representation and may result in information loss, leading to over-smooth and distorted generation. Instead of imposing constraints on the latent representation, in this work we apply an attribute classification constraint to the generated image to just guarantee the correct change of desired attributes, i.e., to "change what you want". Meanwhile, the reconstruction learning is introduced to preserve attribute-excluding details, in other words, to "only change what you want". Besides, the adversarial learning is employed for visually realistic editing. These three components cooperate with each other forming an effective framework for high quality facial attribute editing, referred as AttGAN. Furthermore, our method is also directly applicable for attribute intensity control and can be naturally extended for attribute style manipulation. Experiments on CelebA dataset show that our method outperforms the state-of-the-arts on realistic attribute editing with facial details well preserved.