Related papers: Contrastive Unpaired Translation using Focal Loss …
Image-to-image translation is a new field in computer vision with multiple potential applications in the medical domain. However, for supervised image translation frameworks, co-registered datasets, paired in a pixel-wise sense, are…
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions…
In an unpaired setting, lacking sufficient content constraints for image-to-image translation (I2I) tasks, GAN-based approaches are usually prone to model collapse. Current solutions can be divided into two categories, reconstruction-based…
There has been remarkable recent work in unpaired image-to-image translation. However, they're restricted to translation on single pairs of distributions, with some exceptions. In this study, we extend one of these works to a scalable…
Unsupervised image-to-image translation methods aim to map images from one domain into plausible examples from another domain while preserving structures shared across two domains. In the many-to-many setting, an additional guidance example…
Image-to-image translation plays a vital role in tackling various medical imaging tasks such as attenuation correction, motion correction, undersampled reconstruction, and denoising. Generative adversarial networks have been shown to…
We address the problem of unpaired geometric image-to-image translation. Rather than transferring the style of an image as a whole, our goal is to translate the geometry of an object as depicted in different domains while preserving its…
We cast the problem of image denoising as a domain translation problem between high and low noise domains. By modifying the cycleGAN model, we are able to learn a mapping between these domains on unpaired retinal optical coherence…
Image-to-image translation models have shown remarkable ability on transferring images among different domains. Most of existing work follows the setting that the source domain and target domain keep the same at training and inference…
Contrastive learning is a powerful technique to learn representations that are semantically distinctive and geometrically invariant. While most of the earlier approaches have demonstrated its effectiveness on single-modality learning tasks…
Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the…
Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss. However, such unsupervised methods may generate inferior results…
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this…
Foundation Models (FMs) have been successful in various computer vision tasks like image classification, object detection and image segmentation. However, these tasks remain challenging when these models are tested on datasets with…
Feed-forward CNNs trained for image transformation problems rely on loss functions that measure the similarity between the generated image and a target image. Most of the common loss functions assume that these images are spatially aligned…
Unpaired image-to-image translation (UNIT) aims to map images between two visual domains without paired training data. However, given a UNIT model trained on certain domains, it is difficult for current methods to incorporate new domains…
Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have been achieved using neural nets as data generators,…
Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs) and dual learning. However, existing models lack the ability to control the translated results in the target domain and their results…
Image-to-image translation, which translates input images to a different domain with a learned one-to-one mapping, has achieved impressive success in recent years. The success of translation mainly relies on the network architecture to…
The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rely on additional guidance, such as text prompts or spatial…