Related papers: Scale-arbitrary Invertible Image Downscaling
Preserving original noise residuals in images are critical to image fraud identification. Since the resizing operation during deep learning will damage the microstructures of image noise residuals, we propose a framework for directly…
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel. To improve real world…
Despite variations in architecture and pretraining strategies, recent studies indicate that large-scale AI models often converge toward similar internal representations that also align with neural activity. We propose that scale-invariance,…
Single image super-resolution (SISR) aims to obtain a high-resolution output from one low-resolution image. Currently, deep learning-based SISR approaches have been widely discussed in medical image processing, because of their potential to…
The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the…
Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial images as described by textual queries. Traditional Referring Image…
Deep learning-based algorithms have greatly improved the performance of remote sensing image (RSI) super-resolution (SR). However, increasing network depth and parameters cause a huge burden of computing and storage. Directly reducing the…
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image…
Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…
Limited by imaging systems, the reconstruction of Magnetic Resonance Imaging (MRI) images from partial measurement is essential to medical imaging research. Benefiting from the diverse and complementary information of multi-contrast MR…
Label-free tomographic microscopy offers a compelling means to visualize three-dimensional (3D) refractive index (RI) distributions from two-dimensional (2D) intensity measurements. However, limited forward-model accuracy and the ill-posed…
Recent accelerated MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes…
The goal of attribute manipulation is to control specified attribute(s) in given images. Prior work approaches this problem by learning disentangled representations for each attribute that enables it to manipulate the encoded source…
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these…
Image restoration aims to recover a high-quality clean image from its degraded version. Recent progress in image restoration has demonstrated the effectiveness of All-in-One image restoration models in addressing various unknown…
Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. The most recent deep learning based SISR methods focus…
Magnetic resonance imaging (MRI) with high resolution (HR) provides more detailed information for accurate diagnosis and quantitative image analysis. Despite the significant advances, most existing super-resolution (SR) reconstruction…
Optical aberrations of optical systems cause significant degradation of imaging quality. Aberration correction by sophisticated lens designs and special glass materials generally incurs high cost of manufacturing and the increase in the…
Morphological reconstruction (MR) is often employed by seeded image segmentation algorithms such as watershed transform and power watershed as it is able to filter seeds (regional minima) to reduce over-segmentation. However, MR might…
Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts. Since the complex hybrid distortions, it is hard to restore the distorted…