图像(数学)
计算机科学
忠诚
翻译(生物学)
领域(数学分析)
图像翻译
人工智能
生成语法
过程(计算)
多样性(控制论)
计算机视觉
空格(标点符号)
汽车工业
先验概率
数学
工程类
航空航天工程
贝叶斯概率
操作系统
生物化学
数学分析
电信
信使核糖核酸
基因
化学
作者
Or Greenberg,Eran Kishon,Dani Lischinski
出处
期刊:Cornell University - arXiv
日期:2023-01-01
标识
DOI:10.48550/arxiv.2312.00116
摘要
Image-to-image translation (I2IT) refers to the process of transforming images from a source domain to a target domain while maintaining a fundamental connection in terms of image content. In the past few years, remarkable advancements in I2IT were achieved by Generative Adversarial Networks (GANs), which nevertheless struggle with translations requiring high precision. Recently, Diffusion Models have established themselves as the engine of choice for image generation. In this paper we introduce S2ST, a novel framework designed to accomplish global I2IT in complex photorealistic images, such as day-to-night or clear-to-rain translations of automotive scenes. S2ST operates within the seed space of a Latent Diffusion Model, thereby leveraging the powerful image priors learned by the latter. We show that S2ST surpasses state-of-the-art GAN-based I2IT methods, as well as diffusion-based approaches, for complex automotive scenes, improving fidelity while respecting the target domain's appearance across a variety of domains. Notably, S2ST obviates the necessity for training domain-specific translation networks.
科研通智能强力驱动
Strongly Powered by AbleSci AI