The Mamba architecture has been widely applied to various low-level vision tasks due to its exceptional adaptability and strong performance. Although the Mamba architecture has been adopted for spectral reconstruction, it still faces the following two challenges: (1) Single spatial perception limits the ability to fully understand and analyze hyperspectral images; (2) Single-scale feature extraction struggles to capture the complex structures and fine details present in hyperspectral images. To address these issues, we propose a multi-scale, multi-perceptual Mamba architecture for the spectral reconstruction task, called M3SR. Specifically, we design a multi-perceptual fusion block to enhance the ability of the model to comprehensively understand and analyze the input features. By integrating the multi-perceptual fusion block into a U-Net structure, M3SR can effectively extract and fuse global, intermediate, and local features, thereby enabling accurate reconstruction of hyperspectral images at multiple scales. Extensive quantitative and qualitative experiments demonstrate that the proposed M3SR outperforms existing state-of-the-art methods while incurring a lower computational cost.
MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation
Imperial College London（伦敦帝国学院）；Royal Brompton Hospital（皇家布朗普顿医院）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；University of Cambridge（剑桥大学）
Mamba-Based Modality Disentanglement Network for Multi-Contrast MRI Reconstruction
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院）
MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction
Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Dalian University of Technology（大连理工大学）；Microsoft Research Asia（微软亚洲研究院）；Hong Kong University of Science and Technology（香港科技大学）；School of Computer Science, Peking University（北京大学计算机科学学院）
ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Space Information Research Institute, Hangzhou Dianzi University（杭州电子科技大学空间信息研究院）；Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）
针对工业纹理图像无监督异常定位中图像重建过度泛化与特征重建误差大的问题，提出基于 Mamba 的特征重建与优化方法 ALMRR，通过引入人工模拟异常并修复合成缺陷特征，在多个数据集上优于 SOTA 方法。
PAS-Mamba: Phase-Amplitude-Spatial State Space Model for MRI Reconstruction
School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学）；Big Data Institute, Central South University（大数据研究院，中南大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Science（深圳先进技术研究所，中国科学院）；Department of Orthopaedics, The Second Xiangya Hospital of Central South University（中南大学湘雅医院骨科部）
Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba
Imperial College London（帝国理工学院）；Royal Brompton Hospital（皇家布朗普顿医院）；College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区生物医学工程学院）；Human Phenome Institute, Fudan University（复旦大学人类表型组研究院）；Inselspital, University of Bern（伯尔尼大学因塞尔医院）；Technical University of Munich（慕尼黑工业大学）
DH-Mamba: Exploring Dual-domain Hierarchical State Space Models for MRI Reconstruction
School of Basic Medical Science, Fudan University（复旦大学基础医学院）；Academy of Engineering and Technology, Fudan University（复旦大学工程与技术学院）；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东计算机科学中心（国家济南超级计算中心））
MMR-Mamba: Multi-Modal MRI Reconstruction with Mamba and Spatial-Frequency Information Fusion
The Hong Kong Polytechnic University（香港理工大学）；University of Science and Technology of China（中国科学技术大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Stanford University（斯坦福大学）
GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images
School of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）；School of Information and Communication Engineering, Dalian University of Technology（大连理工大学信息与通信工程学院）；University of Pavia（帕维亚大学）；School of Information and Communication Engineering, Dalian Minzu University（大连民族大学信息与通信工程学院）；School of Innovation and Entrepreneurship, Dalian University of Technology（大连理工大学创新创业学院）
Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction
National University of Singapore（新加坡国立大学）；Singapore Management University（新加坡管理大学）；Nanyang Technological University（南洋理工大学）；Sea AI Lab（Sea AI实验室）；Skywork AI
FaRMamba: Frequency-based learning and Reconstruction aided Mamba for Medical Segmentation
School of Artificial Intelligence and Computer Science, Nantong University, China（人工智能与计算机科学学院，南通大学）；School of Information Science and Technology, Nantong University, China（信息科学与技术学院，南通大学）
We explore the application of volumetric reconstruction from structured-light sensors in cognitive neuroscience, specifically in the quantification of the size-weight illusion, whereby humans tend to systematically perceive smaller objects as heavier. We investigate the performance of two commercial structured-light scanning systems in comparison to one we developed specifically for this application. Our method has two main distinct features: First, it only samples a sparse series of viewpoints, unlike other systems such as the Kinect Fusion. Second, instead of building a distance field for th…
UltrasODM: A Dual Stream Optical Flow Mamba Network for 3D Freehand Ultrasound Reconstruction
Department of Information Technology（信息科技系）；Indian Institute of Information Technology Allahabad Prayagraj（阿拉哈巴德普拉亚格拉杰信息科技学院）；Department of Electronics & Communication Engineering（电子与通信工程系）；Department of Computer Engineering and Mathematics（计算机工程与数学系）；Universitat Rovira i Virgili（罗维拉-维格利大学）
Friedrich-Alexander-Universität（弗里德里希-亚历山大大学）；Imperial College（帝国理工学院）；National Heart & Lung Institute, Imperial College（帝国理工学院国家心肺研究所）；Royal Brompton Hospital（皇家布朗普顿医院）
Deep learning approaches have shown promising performance for compressed sensing-based Magnetic Resonance Imaging. While deep neural networks trained with mean squared error (MSE) loss functions can achieve high peak signal to noise ratio, the reconstructed images are often blurry and lack sharp details, especially for higher undersampling rates. Recently, adversarial and perceptual loss functions have been shown to achieve more visually appealing results. However, it remains an open question how to (1) optimally combine these loss functions with the MSE loss function and (2) evaluate such a p…
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Hunan Engineering Research Center of Machine Vision and Intelligent Medicine, Central South University（中南大学机器视觉与智能医学湖南省工程研究中心）；Department of Nuclear Medicine, Henri Becquerel Cancer Center（亨利·贝克勒尔癌症中心核医学科）；University of Rouen-Normandy（鲁昂-诺曼底大学）
Parameter Aware Mamba Model for Multi-task Dense Prediction
School of Computer Science, Dalian University of Technology（大连理工大学计算机科学学院）；School of Information and Communication Engineering, Dalian University of Technology（大连理工大学信息与通信工程学院）；School of Future Technology and Artificial Intelligence, Dalian University of Technology（大连理工大学未来技术与人工智能学院）
Cross-Scan Mamba with Masked Training for Robust Spectral Imaging
University of Helsinki（赫尔辛基大学）；IMEC（微电子中心）；Universiteit Gent（根特大学）；Northwestern Polytechnical University（西北工业大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction
The Robotics and Mechatronics Group, University of Twente（代尔夫嫩兰道5号，埃因霍温大学机器人与机电组）；The Department of Surgical Oncology, The Netherlands Cancer Institute-Antoni van Leeuwenhoek（荷兰癌症研究所-安托万·李文霍克医院外科肿瘤科）
National Technical University of Athens（雅典国立技术大学）；Imperial College London（伦敦帝国理工学院）；Institute for Language and Speech Processing, Athena R.C.（雅典娜研究中心语言与语音处理研究所）；Foundation for Research & Technology - Hellas（希腊研究与技术基金会）；University of Exeter（埃克塞特大学）
The recent state of the art on monocular 3D face reconstruction from image data has made some impressive advancements, thanks to the advent of Deep Learning. However, it has mostly focused on input coming from a single RGB image, overlooking the following important factors: a) Nowadays, the vast majority of facial image data of interest do not originate from single images but rather from videos, which contain rich dynamic information. b) Furthermore, these videos typically capture individuals in some form of verbal communication (public talks, teleconferences, audiovisual human-computer intera…
Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain Reconstruction
Chonnam National University, Gwangju, Republic of Korea（全罗国立大学，韩国光州市）；Vietnam National University - Ho Chi Minh City, University of Science, Vietnam（越南国家大学-胡志明市，越南科学大学）；Institute for Cybersecurity and Digital Technologies, Russia（俄罗斯网络安全与数字技术研究所）
Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；College of Electronic Science, Air Force Aviation University（空军航空大学电子科学学院）；Intelligent Visual Information Perception Laboratory, Institute of Advanced Technology, Nanjing University of Posts and Telecommunications（南京邮电大学先进技术研究院智能视觉信息感知实验室）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）
Northwestern University（西北大学）；University of Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）
Computed tomography is widely used to examine internal structures in a non-destructive manner. To obtain high-quality reconstructions, one typically has to acquire a densely sampled trajectory to avoid angular undersampling. However, many scenarios require a sparse-view measurement leading to streak-artifacts if unaccounted for. Current methods do not make full use of the domain-specific information, and hence fail to provide reliable reconstructions for highly undersampled data. We present a novel framework for sparse-view tomography by decoupling the reconstruction into two steps: First, we …
ColorMamba: Towards High-quality NIR-to-RGB Spectral Translation with Mamba
School of Computer Science and Engineering, Hunan University of Science and Technology（湖南科技大学计算机科学与工程学院）；Department of Computer Science, Hong Kong Baptist University（香港浸会大学计算机科学系）
ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis
USTC（中国科学技术大学）；NUDT（南京理工大学）；SCNU（华南师范大学）；NTU（南洋理工大学）；Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing（安徽省生物医学成像与智能处理重点实验室）
Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion
School of Future Technology, School of Artificial Intelligence, Dalian University of Technology（大连理工大学未来技术学院、人工智能学院）；Affiliated Zhongshan Hospital of Dalian University（大连大学附属中山医院）；Central Hospital of Dalian University of Technology（大连理工大学中心医院）；School of Information and Communication Engineering, Dalian University of Technology（大连理工大学信息与通信工程学院）
Anyvision（安视维）；Queen’s University Belfast（贝尔法斯特女王大学）
Despite the breakthroughs in quality of image enhancement, an end-to-end solution for simultaneous recovery of the finer texture details and sharpness for degraded images with low resolution is still unsolved. Some existing approaches focus on minimizing the pixel-wise reconstruction error which results in a high peak signal-to-noise ratio. The enhanced images fail to provide high-frequency details and are perceptually unsatisfying, i.e., they fail to match the quality expected in a photo-realistic image. In this paper, we present Image Enhancement Generative Adversarial Network (IEGAN), a ver…
BiSegMamba: Efficient Bidirectional Tri-Oriented Mamba for 3D Medical Image Segmentation
School of Computer Science and Engineering, Beihang University（北航计算机科学与工程学院）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北航虚拟现实技术与系统国家重点实验室）
Dual Hyperspectral Mamba for Efficient Spectral Compressive Imaging
The Hong Kong Polytechnic University（香港理工大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Hunan University（湖南大学）
Spec2VolCAMU-Net: A Spectrogram-to-Volume Model for EEG-to-fMRI Reconstruction based on Multi-directional Time-Frequency Convolutional Attention Encoder and Vision-Mamba U-Net
School of Artificial Intelligence, Chongqing University of Technology（人工智能学院，重庆理工大学）
Roche Innovation Center Munich（慕尼黑罗氏创新中心）；Technische Universität München（慕尼黑工业大学）
Style transfer is a field with growing interest and use cases in deep learning. Recent work has shown Generative Adversarial Networks(GANs) can be used to create realistic images of virtually stained slide images in digital pathology with clinically validated interpretability. Digital pathology images are typically of extremely high resolution, making tilewise analysis necessary for deep learning applications. It has been shown that image generators with instance normalization can cause a tiling artifact when a large image is reconstructed from the tilewise analysis. We introduce a novel perce…
