English
Related papers

Related papers: MST++: Multi-stage Spectral-wise Transformer for E…

200 papers

Convolutional neural networks (CNNs) and vision transformers (ViTs) have achieved remarkable success in various vision tasks. However, many architectures do not consider interactions between feature maps from different stages and scales,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Liang Shang , Yanli Liu , Zhengyang Lou , Shuxue Quan , Nagesh Adluru , Bochen Guan , William A. Sethares

Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Xiangyu Chen , Xintao Wang , Wenlong Zhang , Xiangtao Kong , Yu Qiao , Jiantao Zhou , Chao Dong

Lightweight super resolution networks have extremely importance for real-world applications. In recent years several SR deep learning approaches with outstanding achievement have been introduced by sacrificing memory and computational cost.…

Image and Video Processing · Electrical Eng. & Systems 2020-11-10 Armin Mehri , Parichehr B. Ardakani , Angel D. Sappa

The Resolution of feature maps is critical for medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation are U-Net-like architecture that contains an encoder that utilizes a sequence of…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Chen Wei , Shenghan Ren , Kaitai Guo , Haihong Hu , Jimin Liang

Spatial Transformer Networks (STN) can generate geometric transformations which modify input images to improve the classifier's performance. In this work, we combine the idea of STN with Reinforcement Learning (RL). To this end, we break…

Machine Learning · Computer Science 2021-06-29 Fatemeh Azimi , Federico Raue , Joern Hees , Andreas Dengel

The Swin Transformer image super-resolution (SR) reconstruction network primarily depends on the long-range relationship of the window and shifted window attention to explore features. However, this approach focuses only on global features,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Yuming Huang , Yingpin Chen , Changhui Wu , Binhui Song , Hui Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Bingchen Li , Xin Li , Yiting Lu , Sen Liu , Ruoyu Feng , Zhibo Chen

Low-light image enhancement aims to improve the perception of images collected in dim environments and provide high-quality data support for image recognition tasks. When dealing with photos captured under non-uniform illumination, existing…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Xiao Fang , Xin Gao , Baofeng Li , Feng Zhai , Yu Qin , Zhihang Meng , Jiansheng Lu , Chun Xiao

Multi-stage strategies are frequently employed in image restoration tasks. While transformer-based methods have exhibited high efficiency in single-image super-resolution tasks, they have not yet shown significant advantages over CNN-based…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Ming Cheng , Haoyu Ma , Qiufang Ma , Xiaopeng Sun , Weiqi Li , Zhenyu Zhang , Xuhan Sheng , Shijie Zhao , Junlin Li , Li Zhang

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring…

Image and Video Processing · Electrical Eng. & Systems 2020-01-30 Zongwei Zhou , Md Mahfuzur Rahman Siddiquee , Nima Tajbakhsh , Jianming Liang

We propose a hybrid reconstruction framework for dual-spectral CT (DSCT) that integrates iterative methods with deep learning models. The reconstruction process consists of two complementary components: a knowledge-driven module and a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Ze Yuan , Wenbin Li , Shusen Zhao

Multi-head self-attention (MSA) is a key component of Vision Transformers (ViTs), which have achieved great success in various vision tasks. However, their high computational cost and memory footprint hinder their deployment on…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Kyunghwan Shim , Jaewoong Yun , Shinkook Choi

Recently, single gray/RGB image super-resolution reconstruction task has been extensively studied and made significant progress by leveraging the advanced machine learning techniques based on deep convolutional neural networks (DCNNs).…

Image and Video Processing · Electrical Eng. & Systems 2020-05-26 Junjun Jiang , He Sun , Xianming Liu , Jiayi Ma

Image super-resolution reconstruction is an important task in the field of image processing technology, which can restore low resolution image to high quality image with high resolution. In recent years, deep learning has been applied in…

Image and Video Processing · Electrical Eng. & Systems 2022-10-21 Bolong Zhang , Juan Chen , Quan Wen

Binary neural networks (BNNs) have been widely adopted to reduce the computational cost and memory storage on edge-computing devices by using one-bit representation for activations and weights. However, as neural networks become…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Quang Hieu Vo , Linh-Tam Tran , Sung-Ho Bae , Lok-Won Kim , Choong Seon Hong

Recently, transformers have captured significant interest in the area of single-image super-resolution tasks, demonstrating substantial gains in performance. Current models heavily depend on the network's extensive ability to extract…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Alik Pramanick , Utsav Bheda , Arijit Sur

Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhile, novel deep learning paradigms, e.g., Transformer based…

Computer Vision and Pattern Recognition · Computer Science 2022-07-07 Jiahao Huang , Xiaodan Xing , Zhifan Gao , Guang Yang

We introduce the Convolutional Set Transformer (CST), a novel neural architecture designed to process image sets of arbitrary cardinality that are visually heterogeneous yet share high-level semantics - such as a common category, scene, or…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Federico Chinello , Giacomo Boracchi

Improving the image resolution and acquisition speed of magnetic resonance imaging (MRI) is a challenging problem. There are mainly two strategies dealing with the speed-resolution trade-off: (1) $k$-space undersampling with high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Wenqi Huang , Sen Jia , Ziwen Ke , Zhuo-Xu Cui , Jing Cheng , Yanjie Zhu , Dong Liang

This paper introduces a lightweight image super-resolution (SR) network, termed the Multi-scale Spatial Adaptive Attention Network (MSAAN), to address the common dilemma between high reconstruction fidelity and low model complexity in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Sushi Rao , Jingwei Li