Related papers: One-for-All: Towards Universal Domain Translation with a Single StyleGAN

One-for-All: Towards Universal Domain Translation with a Single StyleGAN

URL: http://arxiv.org/abs/2310.14222v1
Date: Sun, 22 Oct 2023 08:02:55 GMT
Title: One-for-All: Towards Universal Domain Translation with a Single StyleGAN
Authors: Yong Du, Jiahui Zhan, Shengfeng He, Xinzhe Li, Junyu Dong, Sheng Chen, and Ming-Hsuan Yang
Abstract summary: We propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains. The proposed UniTranslator is versatile and capable of performing various tasks, including style mixing, stylization, and translations. UniTranslator surpasses the performance of existing general-purpose models and performs well against specialized models in representative tasks.
Score: 86.33216867136639
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and significant visual differences. The main idea behind our approach is leveraging the domain-neutral capabilities of CLIP as a bridging mechanism, while utilizing a separate module to extract abstract, domain-agnostic semantics from the embeddings of both the source and target realms. Fusing these abstract semantics with target-specific semantics results in a transformed embedding within the CLIP space. To bridge the gap between the disparate worlds of CLIP and StyleGAN, we introduce a new non-linear mapper, the CLIP2P mapper. Utilizing CLIP embeddings, this module is tailored to approximate the latent distribution in the P space, effectively acting as a connector between these two spaces. The proposed UniTranslator is versatile and capable of performing various tasks, including style mixing, stylization, and translations, even in visually challenging scenarios across different visual domains. Notably, UniTranslator generates high-quality translations that showcase domain relevance, diversity, and improved image quality. UniTranslator surpasses the performance of existing general-purpose models and performs well against specialized models in representative tasks. The source code and trained models will be released to the public.