中文
相关论文

相关论文: DeRainMamba: A Frequency-Aware State Space Model w…

200 篇论文

Image deraining aims to remove rain streaks from rainy images and restore clear backgrounds. Currently, some research that employs the Fourier transform has proved to be effective for image deraining, due to it acting as an effective…

计算机视觉与模式识别 · 计算机科学 2024-08-08 Dong Li , Yidi Liu , Xueyang Fu , Senyan Xu , Zheng-Jun Zha

Removing rain degradations in images is recognized as a significant issue. In this field, deep learning-based approaches, such as Convolutional Neural Networks (CNNs) and Transformers, have succeeded. Recently, State Space Models (SSMs)…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Shugo Yamashita , Masaaki Ikehara

Images corrupted by rain streaks often lose vital frequency information for perception, and image deraining aims to solve this issue which relies on global and local degradation modeling. Recent studies have witnessed the effectiveness and…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Zou Zhen , Yu Hu , Zhao Feng

The outdoor vision systems are frequently contaminated by rain streaks and raindrops, which significantly degenerate the performance of visual tasks and multimedia applications. The nature of videos exhibits redundant temporal cues for rain…

计算机视觉与模式识别 · 计算机科学 2024-09-12 Hongtao Wu , Yijun Yang , Huihui Xu , Weiming Wang , Jinni Zhou , Lei Zhu

Event cameras excel in high temporal resolution and dynamic range but suffer from dense noise in rainy conditions. Existing event deraining methods face trade-offs between temporal precision, deraining effectiveness, and computational…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Ciyu Ruan , Ruishan Guo , Zihang Gong , Jingao Xu , Wenhan Yang , Xinlei Chen

Image deraining is an essential vision technique that removes rain streaks and water droplets, enhancing clarity for critical vision tasks like autonomous driving. However, current single-scale models struggle with fine-grained recovery and…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Pengze Xue , Shanwen Wang , Fei Zhou , Yan Cui , Xin Sun

Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Leiye Liu , Miao Zhang , Jihao Yin , Tingwei Liu , Wei Ji , Yongri Piao , Huchuan Lu

Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch…

计算机视觉与模式识别 · 计算机科学 2024-09-04 Shangquan Sun , Wenqi Ren , Juxiang Zhou , Jianhou Gan , Rui Wang , Xiaochun Cao

Rain significantly degrades the performance of computer vision systems, particularly in applications like autonomous driving and video surveillance. While existing deraining methods have made considerable progress, they often struggle with…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Zhaocheng Yu , Kui Jiang , Junjun Jiang , Xianming Liu , Guanglu Sun , Yi Xiao

This paper proposes ControlMambaIR, a novel image restoration method designed to address perceptual challenges in image deraining, deblurring, and denoising tasks. By integrating the Mamba network architecture with the diffusion model, the…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Cheng Yang , Lijing Liang , Zhixun Su

Traffic image restoration under adverse weather conditions remains a critical challenge for intelligent transportation systems. Existing methods primarily focus on spatial-domain modeling but neglect frequency-domain priors. Although the…

计算机视觉与模式识别 · 计算机科学 2025-12-04 Liwen Pan , Longguang Wang , Guangwei Gao , Jun Wang , Jun Shi , Juncheng Li

Remote sensing image fusion aims to generate a high-resolution multi/hyper-spectral image by combining a high-resolution image with limited spectral data and a low-resolution image rich in spectral information. Current deep learning (DL)…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Siran Peng , Xiangyu Zhu , Haoyu Deng , Liang-Jian Deng , Zhen Lei

Image restoration endeavors to reconstruct a high-quality, detail-rich image from a degraded counterpart, which is a pivotal process in photography and various computer vision systems. In real-world scenarios, different types of degradation…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Yuhong He , Long Peng , Qiaosi Yi , Chen Wu , Lu Wang

Denoising is a crucial preprocessing step for hyperspectral images (HSIs) due to noise arising from intra-imaging mechanisms and environmental factors. Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but…

图像与视频处理 · 电气工程与系统科学 2024-08-06 Guanyiman Fu , Fengchao Xiong , Jianfeng Lu , Jun Zhou

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Mohammed Hassanin , Nour Moustafa , Weijian Deng , Ibrahim Radwan

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…

计算机视觉与模式识别 · 计算机科学 2025-02-04 Xinyu Xie , Yawen Cui , Tao Tan , Xubin Zheng , Zitong Yu

We introduce a novel state-space architecture for diffusion models, effectively harnessing spatial and frequency information to enhance the inductive bias towards local features in input images for image generation tasks. While state-space…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Hao Phung , Quan Dao , Trung Dao , Hoang Phan , Dimitris Metaxas , Anh Tran

Accurate medical image segmentation requires effective modeling of both global anatomical structures and fine-grained boundary details. Recent state space models (e.g., Vision Mamba) offer efficient long-range dependency modeling. However,…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Fuhao Zhang , Lei Liu , Jialin Zhang , Ya-Nan Zhang , Nan Mu

Image shadow removal is a typical low-level vision task. Shadows cause local brightness shifts, which reduce the performance of downstream vision tasks. Currently, Transformer-based shadow removal methods suffer from quadratic computational…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Xiujin Zhu , Chee-Onn Chow , Joon Huang Chuah

Low-light image enhancement remains a persistent challenge in computer vision, where state-of-the-art models are often hampered by hardware constraints and computational inefficiency, particularly at high resolutions. While foundational…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Eashan Adhikarla , Kai Zhang , Gong Chen , John Nicholson , Brian D. Davison
‹ 上一页 1 2 3 10 下一页 ›