# Image-to-Image Translation with Low Resolution Conditioning Source: [Image-to-Image Translation with Low Resolution Conditioning]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:10:14.287Z Authors: Mohamed Abderrahmen Abid, Ihsen Hedhli, Jean-Fran\\c{c}ois Lalonde, Christian Gagne Published: 2021-07-23T14:22:12.000Z ## Abstract Most image-to-image translation methods focus on learning mappings across domains with the assumption that images share content (e.g., pose) but have their own domain-specific information known as style. When conditioned on a target image, such methods aim to extract the style of the target and combine it with the content of the source image. In this work, we consider the scenario where the target image has a very low resolution. More specifically, our approach aims at transferring fine details from a high resolution (HR) source image to fit a coarse, low resolution (LR) image representation of the target. We therefore generate HR images that share features from both HR and LR inputs. This differs from previous methods that focus on translating a given image style into a target content, our translation approach being able to simultaneously imitate the style and merge the structural information of the LR target. Our approach relies on training the generative model to produce HR target images that both 1) share distinctive information of the associated source image; 2) correctly match the LR target image when downscaled. We validate our method on the CelebA-HQ and AFHQ datasets by demonstrating improvements in terms of visual quality, diversity and coverage. Qualitative and quantitative results show that when dealing with intra-domain image translation, our method generates more realistic samples compared to state-of-the-art methods such as Stargan-v2 ## 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. - [Reference-guided image synthesis on CelebA-HQ 128 x 128](): Reference-guided image synthesis; CelebA-HQ 128 x 128; Density: 1.97. - [Reference-guided image synthesis on CelebA-HQ 256x256](): Reference-guided image synthesis; CelebA-HQ 256 x 256; Density: 1.87. - [Reference-guided image synthesis on CelebA-HQ (test)](): Reference-guided image synthesis; CelebA-HQ (test); FID: 15.52. ## Original sources and implementation [Original paper]() [PDF]()