paper-with-me

홈 › Papers

Disentangled Image Generation Through Structured Noise Injection

2020-04-26 · CVPR 2020 6 · Yazeed Alharbi, Peter Wonka

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.

📄 PDF Abstract BibTeX arXiv:2004.12411

Code (1)

yalharbi/StructuredNoiseInjection tf

Tasks

DisentanglementImage Generation

Similar Papers 제목 키워드 기반

Image Generation and Translation with Disentangled Representations

2018-03-28 · Tobias Hinz, Stefan Wermter

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+2

OmniPrism: Learning Disentangled Visual Concept for Image Generation

2024-12-16 · Yangyang Li, Daqing Liu, Wu Liu, Allen He 외

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 Generation

Animating Face using Disentangled Audio Representations

2019-10-02 · Gaurav Mittal, Baoyuan Wang

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 Generation

Class Conditional Time Series Generation with Structured Noise Space GAN

2023-12-20 · Hamidreza Gholamrezaei, Alireza Koochali, Andreas Dengel, Sheraz Ahmed

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 Generation

Identifying Coarse-grained Independent Causal Mechanisms with Self-supervision

2021-01-01 · 1st Conference on Causal Learning and Reasoning 2022 2 · Xiaoyang Wang, Klara Nahrstedt, Oluwasanmi O Koyejo

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 …