Related papers: SEAL: A Framework for Systematic Evaluation of Rea…
Most super-resolution (SR) models struggle with real-world low-resolution (LR) images. This issue arises because the degradation characteristics in the synthetic datasets differ from those in real-world LR images. Since SR models are…
Single image super resolution is a very important computer vision task, with a wide range of applications. In recent years, the depth of the super-resolution model has been constantly increasing, but with a small increase in performance, it…
Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these…
Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer videos. Our key insight is that many regions in video are…
This paper proposes a simple, accurate, and robust approach to single image nonparametric blind Super-Resolution (SR). This task is formulated as a functional to be minimized with respect to both an intermediate super-resolved image and a…
Recent advances in generative super-resolution (SR) have greatly improved visual realism, yet existing evaluation and optimization frameworks remain misaligned with human perception. Full-Reference and No-Reference metrics often fail to…
Given an image, we wish to produce an image of larger size with significantly more pixels and higher image quality. This is generally known as the Single Image Super-Resolution (SISR) problem. The idea is that with sufficient training data…
Most existing face image Super-Resolution (SR) methods assume that the Low-Resolution (LR) images were artificially downsampled from High-Resolution (HR) images with bicubic interpolation. This operation changes the natural image…
Most deep learning-based super-resolution (SR) methods are not image-specific: 1) They are trained on samples synthesized by predefined degradations (e.g. bicubic downsampling), regardless of the domain gap between training and testing…
Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented…
Retrieval-Augmented Generation (RAG) is a core approach for enhancing Large Language Models (LLMs), where the effectiveness of the retriever largely determines the overall response quality of RAG systems. Retrievers encompass a multitude of…
Modern deep Super-Resolution (SR) networks have established themselves as valuable techniques in image reconstruction and enhancement. However, these networks are normally trained and tested on benchmark image data that lacks the typical…
Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic…
Diffusion magnetic resonance imaging (dMRI) often suffers from low spatial and angular resolution due to inherent limitations in imaging hardware and system noise, adversely affecting the accurate estimation of microstructural parameters…
Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic data. However, their performance on real-world video data…
Event cameras are a new type of vision sensor that incorporates asynchronous and independent pixels, offering advantages over traditional frame-based cameras such as high dynamic range and minimal motion blur. However, their output is not…
Reference-based Super Resolution (RefSR) improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance texture fidelity and visual realism. However, a critical limitation of existing RefSR…
This paper investigates the problem of Generalized Category Discovery (GCD). Given a partially labelled dataset, GCD aims to categorize all unlabelled images, regardless of whether they belong to known or unknown classes. Existing…
We aim at accelerating super-resolution (SR) networks on large images (2K-8K). The large images are usually decomposed into small sub-images in practical usages. Based on this processing, we found that different image regions have different…
Deep neural networks have exhibited promising performance in image super-resolution (SR) by learning a nonlinear mapping function from low-resolution (LR) images to high-resolution (HR) images. However, there are two underlying limitations…