We introduce CAFLOW, a new diverse image-to-image translation model that simultaneously leverages the power of auto-regressive modeling and the modeling efficiency of conditional normalizing flows. We transform the conditioning image into a sequence of latent encodings using a multi-scale normalizing flow and repeat the process for the conditioned image. We model the conditional distribution of the latent encodings by modeling the auto-regressive distributions with an efficient multi-scale normalizing flow, where each conditioning factor affects image synthesis at its respective resolution scale. Our proposed framework performs well on a range of image-to-image translation tasks. It outperforms former designs of conditional flows because of its expressive auto-regressive structure.

翻译：我们引入了一个新的不同图像到图像翻译模型CAFLOW, 这个模型可以同时利用自动递减模型的功率和有条件正常流的模型效率。 我们用多尺度的正常流将调节图像转换成潜在编码序列, 并重复有条件图像的过程。 我们用一个高效的多尺度正常流模拟自动递减分布模式来模拟潜在编码的有条件分布, 每个调节因素都会影响图像的分辨率合成。 我们提议的框架在一系列图像到图像的模型翻译任务上表现良好。 由于它具有显性自动递减结构, 它比以前的有条件流动设计要好。