相关论文: Fast GPU-Enabled Color Normalization for Digital P…

Convolutional Neural Networks (CNN)-based approaches have shown promising results in pansharpening of satellite images in recent years. However, they still exhibit limitations in producing high-quality pansharpening outputs. To that end, we…

The goal of computational color constancy is to preserve the perceptive colors of objects under different lighting conditions by removing the effect of color casts caused by the scene's illumination. With the rapid development of deep…

The potential of artificial intelligence (AI) in digital pathology is limited by technical inconsistencies in the production of whole slide images (WSIs), leading to degraded AI performance and posing a challenge for widespread clinical…

With the widespread application of convolutional neural networks (CNNs), the traditional model based denoising algorithms are now outperformed. However, CNNs face two problems. First, they are computationally demanding, which makes their…

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline…

Dermoscopic skin images are often obtained with different imaging devices, under varying acquisition conditions. In this work, instead of attempting to perform intensity and color normalization, we propose to leverage computational color…

Deep learning advances have revolutionized automated digital pathology analysis. However, differences in staining protocols and imaging conditions can introduce significant color variability. In deep learning, such color inconsistency often…

Computer-generated graphics (CGs) are images generated by computer software. The~rapid development of computer graphics technologies has made it easier to generate photorealistic computer graphics, and these graphics are quite difficult to…

Grayscale image colorization is a fascinating application of AI for information restoration. The inherently ill-posed nature of the problem makes it even more challenging since the outputs could be multi-modal. The learning-based methods…

In recent years, spiking neural networks (SNNs) emerge as an alternative to deep neural networks (DNNs). SNNs present a higher computational efficiency using low-power neuromorphic hardware and require less labeled data for training using…

Noise removal in the standard RGB (sRGB) space remains a challenging task, in that the noise statistics of real-world images can be different in R, G and B channels. In fact, the green channel usually has twice the sampling rate in raw data…

Deep neural networks have been successfully applied to problems such as image segmentation, image super-resolution, coloration and image inpainting. In this work we propose the use of convolutional neural networks (CNN) for image inpainting…

Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end,…

Batch Normalization (BN) has become an out-of-box technique to improve deep network training. However, its effectiveness is limited for micro-batch training, i.e., each GPU typically has only 1-2 images for training, which is inevitable for…

Graph convolutional networks (GCNs) have emerged as a powerful alternative to multiple instance learning with convolutional neural networks in digital pathology, offering superior handling of structural information across various spatial…

While hematoxylin and eosin (H&E) is a standard staining procedure, immunohistochemistry (IHC) staining further serves as a diagnostic and prognostic method. However, acquiring special staining results requires substantial costs. Hence, we…

While there have been many studies on hardware acceleration for deep learning on images, there has been a rather limited focus on accelerating deep learning applications involving graphs. The unique characteristics of graphs, such as the…

Foundation models have revolutionized computational pathology by achieving remarkable success in high-level diagnostic tasks, yet the critical challenge of low-level image enhancement remains largely unaddressed. Real-world pathology images…

Tissue characterization has long been an important component of Computer Aided Diagnosis (CAD) systems for automatic lesion detection and further clinical planning. Motivated by the superior performance of deep learning methods on various…

We introduce a deep learning approach to realistically edit an sRGB image's white balance. Cameras capture sensor images that are rendered by their integrated signal processor (ISP) to a standard RGB (sRGB) color space encoding. The ISP…