Related papers: Unsupervised Image Noise Modeling with Self-Consis…

Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…

Conditional image generation is effective for diverse tasks including training data synthesis for learning-based computer vision. However, despite the recent advances in generative adversarial networks (GANs), it is still a challenging task…

The lack of large-scale real raw image denoising dataset gives rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies…

Deep neural network based methods are the state of the art in various image restoration problems. Standard supervised learning frameworks require a set of noisy measurement and clean image pairs for which a distance between the output of…

In this work, we present SupResDiffGAN, a novel hybrid architecture that combines the strengths of Generative Adversarial Networks (GANs) and diffusion models for super-resolution tasks. By leveraging latent space representations and…

The detection and the quantification of anomalies in image data are critical tasks in industrial scenes such as detecting micro scratches on product. In recent years, due to the difficulty of defining anomalies and the limit of correcting…

Image enhancement approaches often assume that the noise is signal independent, and approximate the degradation model as zero-mean additive Gaussian. However, this assumption does not hold for biomedical imaging systems where sensor-based…

Deep neural networks have been proved efficient for medical image denoising. Current training methods require both noisy and clean images. However, clean images cannot be acquired for many practical medical applications due to naturally…

Ultrasound (US) is widely accepted in clinic for anatomical structure inspection. However, lacking in resources to practice US scan, novices often struggle to learn the operation skills. Also, in the deep learning era, automated US image…

A plethora of machine learning methods have been applied to imaging data, enabling the construction of clinically relevant imaging signatures of neurological and neuropsychiatric diseases. Oftentimes, such methods don't explicitly model the…

We consider the task of photo-realistic unconditional image generation (generate high quality, diverse samples that carry the same visual content as the image) on mobile platforms using Generative Adversarial Networks (GANs). In this paper,…

Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for modern methods that leverage deep neural networks trained to…

Self-supervised frameworks that learn denoising models with merely individual noisy images have shown strong capability and promising performance in various image denoising tasks. Existing self-supervised denoising frameworks are mostly…

This paper reports on WaterGAN, a generative adversarial network (GAN) for generating realistic underwater images from in-air image and depth pairings in an unsupervised pipeline used for color correction of monocular underwater images.…

In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic. By defining two convolutional neural networks (G-Network and D-Network) and introducing an adversarial procedure between them during the training…

Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding high-quality images. While high-quality image acquisition is…

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…

Machine Learning, particularly Generative Adversarial Networks (GANs), has revolutionised Super-Resolution (SR). However, generated images often lack physical meaningfulness, which is essential for scientific applications. Our approach,…

Although the recent advancement in generative models brings diverse advantages to society, it can also be abused with malicious purposes, such as fraud, defamation, and fake news. To prevent such cases, vigorous research is conducted to…

In this paper, we present InSeGAN, an unsupervised 3D generative adversarial network (GAN) for segmenting (nearly) identical instances of rigid objects in depth images. Using an analysis-by-synthesis approach, we design a novel GAN…