2022/03/29 by Kun Hee Kim, Kim, Kunhee, Sanghun Park +7 · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Cancer-related molecular mechanisms research #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Video Analysis and Summarization
paper · pdf · doi:10.48550/arxiv.2203.15375
openalex publication_date 2022/03/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Current image-to-image translations do not control the output domain beyond the classes used during training, nor do they interpolate between different domains well, leading to implausible results. This limitation largely arises because labels do not consider the semantic distance. To mitigate such problems, we propose a style-aware discriminator that acts as a critic as well as a style encoder to provide conditions. The style-aware discriminator learns a controllable style space using prototype-based self-supervised learning and simultaneously guides the generator. Experiments on multiple datasets verify that the proposed model outperforms current state-of-the-art image-to-image translation methods. In contrast with current methods, the proposed approach supports various applications, including style interpolation, content transplantation, and local image translation.