# A Style-aware Discriminator for Controllable Image Translation

Source: [A Style-aware Discriminator for Controllable Image Translation](<https://www.sota2.com/research/paper/68fa6c161e209131cea3210e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:03:49.010Z

Authors: Kunhee Kim, Sanghun Park, Eunyeong Jeon, Taehun Kim, Daijin Kim

Published: 2022-03-29T09:13:33.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image-to-Image Translation on Food-10](<https://www.sota2.com/research/sota/image-to-image-translation-on-food-10.md>): Image-to-Image Translation; Food-10; mFID: 49.34.

- [Image-to-Image Translation on CelebA-HQ gender as class (test)](<https://www.sota2.com/research/sota/image-to-image-translation-on-celeba-hq-gender-as-class-test.md>): Image-to-Image Translation; CelebA-HQ gender as class (test); TC: 10.462.

- [Image-to-Image Translation on AnimalFaces-10](<https://www.sota2.com/research/sota/image-to-image-translation-on-animalfaces-10.md>): Image-to-Image Translation; AnimalFaces-10; mFID: 36.83.

- [Image-to-Image Translation on AFHQ 3 classes (test)](<https://www.sota2.com/research/sota/image-to-image-translation-on-afhq-3-classes-test.md>): Image-to-Image Translation; AFHQ 3 classes (test); TC: 3.241.

- [Image-to-Image Translation on CelebA-HQ](<https://www.sota2.com/research/sota/image-to-image-translation-on-celeba-hq.md>): Image-to-Image Translation; CelebA-HQ; FID: 41.33.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.15375>)

[PDF](<https://arxiv.org/pdf/2203.15375.pdf>)