Disentangled Image Generation Through Structured Noise Injection
We explore different design choices for injecting noise into generative adversarial networks (GANs) with the goal of disentangling the latent space. Instead of traditional approaches, we propose feeding multiple noise codes through separate fully-connected layers respectively. The aim is restricting the influence of each noise code to specific parts of the generated image. We show that disentanglement in the first layer of the generator network leads to disentanglement in the generated image. Through a grid-based structure, we achieve several aspects of disentanglement without complicating the network architecture and without requiring labels. We achieve spatial disentanglement, scale-space disentanglement, and disentanglement of the foreground object from the background style allowing fine-grained control over the generated images. Examples include changing facial expressions in face images, changing beak length in bird images, and changing car dimensions in car images. This empirically leads to better disentanglement scores than state-of-the-art methods on the FFHQ dataset.
Code (1)
Tasks
DisentanglementImage GenerationSimilar Papers 제목 키워드 기반
Image Generation and Translation with Disentangled Representations
Generative models have made significant progress in the tasks of modeling complex data distributions such as natural images. The introduction of Generative Adversarial Networks (GANs) and auto-encoders lead to the possib…
Conditional Image GenerationFace GenerationImage GenerationImage-to-Image Translation+2OmniPrism: Learning Disentangled Visual Concept for Image Generation
Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation…
DisentanglementImage GenerationAnimating Face using Disentangled Audio Representations
All previous methods for audio-driven talking head generation assume the input audio to be clean with a neutral tone. As we show empirically, one can easily break these systems by simply adding certain background noise t…
Representation LearningTalking Head GenerationClass Conditional Time Series Generation with Structured Noise Space GAN
This paper introduces Structured Noise Space GAN (SNS-GAN), a novel approach in the field of generative modeling specifically tailored for class-conditional generation in both image and time series data. It addresses the…
Time SeriesTime Series GenerationIdentifying Coarse-grained Independent Causal Mechanisms with Self-supervision
Current approaches for learning disentangled representations assume that independent latent variables generate the data through a single data generation process. In contrast, this manuscript considers independent causal …