RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes

By Po-Wei Wu, Yu-Jing Lin, Che-Han Chang, Edward Y. Chang, Shih-Wei Liao. 2019

160 citations recorded by the source corpus.

Multi-domain image-to-image translation has gained increasing attention recently. Previous methods take an image and some target attributes as inputs and generate an output image with the desired attributes. However, such methods have two limitations. First, these methods assume binary-valued attributes and thus cannot yield satisfactory results for fine-grained control. Second, these methods require specifying the entire set of target attributes, even if most of the attributes would not be changed. To address these limitations, we propose RelGAN, a new method for multi-domain image-to-image translation. The key idea is to use relative attributes, which describes the desired change on selected attributes. Our method is capable of modifying images by changing particular attributes of interest in a continuous manner while preserving the other attributes. Experimental results demonstrate both the quantitative and qualitative effectiveness of our method on the tasks of facial attribute transfer and interpolation.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Diffusion Autoencoders: Toward a Meaningful and Decodable Representation (2021, background): “Besides producing impressive image samples, GANs [15] have been shown to learn meaningful latent spaces [27] with extensive studies on multiple derived spaces [24, 57] and various knobs and controls for conditional human face generation [21, 37, 55].”
Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation (2021, unknown): “We compare our method to several popular frameworks, from existing image-to-image translation methods (Choi et al., 2020; Wu et al., 2019; Zhu et al., 2017a) to latent space transformation-based approaches (Shen et al.”
Image-to-Image Translation: Methods and Applications (2021, background): “Attribute manipulation \ \ [75], [133], [134], [139], [145] [77] \ [156] [162], [163], [158], [159], [160], [161], [165], [164], [167], [169], [170] [171], [172], [31], [173], [174], [175] [176], [178] [176] [17], [179]”
Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators? (2020, methodology): “To solve this problem, numerous methods built on conditional GAN models [8, 12, 17, 18, 28] are proposed, and they typically focus on designing new loss functions or improving network structures.”
Detection of AI-Generated Synthetic Faces (2022, methodology): “The test dataset comprises both same-resolution and higher resolution (1024× 1024) images generated by various GANarchitectures: StyleGAN [27], StyleGAN2 [28], BigGAN [6], CycleGAN [62], StarGAN [10], RelGAN [55], and GauGAN [44].”
Disentangled Face Attribute Editing via Instance-Aware Latent Space Search (2021, methodology): “These methods usually design the loss function [Shen and Liu, 2017; Bahng et al. , 2020; Zhu et al. , 2017 ] or network architecture [Choi et al. , 2018; Zhang et al. , 2018; Liu et al. , 2019; Lin et al. , 2019; He et al. , 2019] manually to improve the output quality.”
Media Forensics and DeepFakes: An Overview (2020, background): “These include content generation [22], [23], image/video synthesis from semantic labels [24], [25] or sketches [26] or text [27], changes of style and attributes [22], [28], [29], domain translation [30], up to expression transfer [25], face swapping typical of deepfakes [31] and talking-head video ”