检索结果-内蒙古大学图书馆

Enhanced multi-stage network for defocus deblurring using dual-pixel images 13

学校读者我要写书评

暂无评论

Enhanced multi-stage network for defocus deblurring using du...

13th International Conference on Signal Processing Systems, ICSPS 2021

作者： Li, Ru Xie, Junwei Xue, Yuyang Zou, Wenbin Tong, Tong Luo, Ming Gao, Qinquan College of Physics and Information Engineering Fuzhou University China Fujian Key Lab of Medical Instrumentation & Pharmaceutical Technology Fuzhou University China Imperial Vision Technology Fujian China Department of Computer Science University of Tsukuba Tsukuba Japan Fujian Provincial Key Laboratory of Photonics Technology Fujian Normal University China

ISBN: (数字)9781510653184

ISBN: (纸本)9781510653177

The defocus deblurring raised from the finite aperture size and exposure time is an essential problem in the shooting process, which seriously affects the quality of the images. However, studies based on defocus deblurring in monocular images yielded good results, while those on binocular images are rare. The current methods directly merge the left and right views regardless of their unique features. Objects within the camera's DoF will not have a difference in phase, while light rays from outside the DoF will have a relative shift that is directly correlated with the amount of defocus blur. In this paper, we firstly proposed an enhanced multi-stage network for defocus deblurring using dual-pixel Images. Taking into account the parallax between the left and right views, the first two stages learn the information of them, respectively, and correct the deviation of the images under the supervision of the ground truth. The third stage consists of EERG and ERGS. It merges with the feature map of the previous stage, so that the left and right views are mutually enhanced, and a good restored image is obtained. ERGS uses the residual block as the basic unit to restore the details of the blurred area while maintaining the clear. Experimental results show that our proposed network can achieve better accuracy than state-of-the-art approaches on the public DPD dataset. © COPYRIGHT SPIE.

关键词： Geometrical optics

Tera-MIND: Tera-scale mouse brain simulation via spatial mRNA-guided diffusion

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Jiqing Berg, Ingrid Li, Yawei Konukoglu, Ender Koelzer, Viktor H. Department of Biomedical Engineering University of Basel Switzerland Department of Pathology and Molecular Pathology University Hospital University of Zurich Switzerland Computer Vision Lab ETH Zurich Switzerland Integrated System Laboratory ETH Zurich Switzerland Institute of Medical Genetics and Pathology University Hospital Basel Switzerland

Holistic 3D modeling of molecularly defined brain structures is crucial for understanding complex brain functions. Emerging tissue profiling technologies enable the construction of a comprehensive atlas of the mammalian brain with sub-cellular resolution and spatially resolved gene expression data. However, such tera-scale volumetric datasets present significant computational challenges in understanding complex brain functions within their native 3D spatial context. Here, we propose the novel generative approach Tera-MIND, which can simulate Tera-scale Mouse braINs in 3D using a patch-based and boundary-aware Diffusion model. Taking spatial transcriptomic data as the conditional input, we generate virtual mouse brains with comprehensive cellular morphological detail at teravoxel scale. Through the lens of 3D gene-gene self-attention, we identify spatial molecular interactions for key transcriptomic pathways in the murine brain, exemplified by glutamatergic and dopaminergic neuronal systems. Importantly, these in-silico biological findings are consistent and reproducible across three tera-scale virtual mouse brains. Therefore, Tera-MIND showcases a promising path toward efficient and generative simulations of whole organ systems for biomedical research. Project website: https://***/*** © 2025, CC BY.

关键词： Mammals

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shen, Haoran Zhang, Yifu Wang, Wenxuan Chen, Chen Liu, Jing Song, Shanshan Li, Jiangyun School of Automation and Electrical Engineering University of Science and Technology Beijing China Center for Research in Computer Vision University of Central Florida United States National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet [44]) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational efficiency

A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ji, Haoqin Liu, Haozhe Li, Yuexiang Xie, Jinheng He, Nanjun Huang, Yawen Wei, Dong Chen, Xinrong Shen, Linlin Zheng, Yefeng Computer Vision Institute College of Computer Science and Software Engineering China AI Research Center for Medical Image Analysis & Diagnosis Shenzhen University China Jarvis Lab Tencent China Academy for Engineering and Technology Fudan University China

Accurate abnormality localization in chest X-rays (CXR) can benefit the clinical diagnosis of various thoracic diseases. However, the lesion-level annotation can only be performed by experienced radiologists, and it is tedious and time-consuming, thus difficult to acquire. Such a situation results in a difficulty to develop a fully-supervised abnormality localization system for CXR. In this regard, we propose to train the CXR abnormality localization framework via a weakly semi-supervised strategy, termed Point Beyond Class (PBC), which utilizes a small number of fully annotated CXRs with lesion-level bounding boxes and extensive weakly annotated samples by points. Such a point annotation setting can provide weakly instance-level information for abnormality localization with a marginal annotation cost. Particularly, the core idea behind our PBC is to learn a robust and accurate mapping from the point annotations to the bounding boxes against the variance of annotated points. To achieve that, a regularization term, namely multi-point consistency, is proposed, which drives the model to generate the consistent bounding box from different point annotations inside the same abnormality. Furthermore, a self-supervision, termed symmetric consistency, is also proposed to deeply exploit the useful information from the weakly annotated data for abnormality localization. Experimental results on RSNA and VinDr-CXR datasets justify the effectiveness of the proposed method. When ≤20% box-level labels are used for training, an improvement of ∼5% in mAP can be achieved by our PBC, compared to the current state-of-the-art method (i.e., Point DETR). Code is available at https://***/HaozheLiu-ST/Point-Beyond-Class. Copyright © 2022, The Authors. All rights reserved.

关键词： Digital storage

Mpfc-Net: A Skin Lesion Segmentation Algorithm with Multi-Path Fusion Convolution

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Cao, Jiaxuan Li, Yang Yan, Junfeng Zou, Beiji Zhao, Guoying Liu, Qingping School of Informatics Hunan University of Chinese Medicine Changsha410208 China AI TCM Lab Hunan Changsha410699 China School of Computer Science and Engineering Central South University Changsha410083 China Center for Machine Vision and Signal Analysis University of Oulu Finland

Skin lesion segmentation plays a crucial role in the early detection and accurate skin cancer diagnosis. The complex network architectures in existing studies fail to meet the requirements for rapid segmentation in practical applications and cannot extract effective features from different depth feature layers, leading to poor segmentation results. To address the above issues, this paper proposes a skin cancer lesion segmentation algorithm based on multi-path fusion convolution, named MPFC-Net. A shallow feature acquisition module is developed to reduce computational costs and retain more contour features. A new downsampling module with a dual-branch structure is designed to compensate for feature loss. A multi-path fusion convolution module is proposed to enable the network to fully learn contextual information and better adapt to complex situations such as varying lesion morphology and blurred edges. Experiments are conducted on the ISIC-2018 public dataset to segment skin cancer lesions under noisy interference background, achieving accuracy rates of 96.07%, mIoU indices of 81.87%, and Dice indices of 88.57%. Compared with other state-of-the-art methods, the performance of MPFC-Net obtains excellent results in all metrics, validating the effectiveness and feasibility of MPFC-Net. © 2024, The Authors. All rights reserved.

关键词： Image segmentation

NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report

学校读者我要写书评

暂无评论

NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Ancuti, Codruta O. Ancuti, Cosmin Vasluianu, Florin-Alexandru Timofte, Radu Zhou, Han Dong, Wei Liu, Yangyi Chen, Jun Liu, Huan Li, Liangyan Wu, Zijun Dong, Yubo Li, Yuyan Qiu, Tian He, Yu Lu, Yonghong Wu, Yinwei Jiang, Zhenxiang Liu, Songhua Yang, Xingyi Jing, Yongcheng Benjdira, Bilel Ali, Anas M. Koubaa, Anis Yang, Hao-Hsiang Chen, I-Hsiang Chen, Wei-Ting Huang, Zhi-Kai Chen, Yi-Chung Hsieh, Chia-Hsuan Chang, Hua-En Chiang, Yuan-Chun Kuo, Sy-Yen Guo, Yu Gao, Yuan Liu, Ryan Wen Lu, Yuxu Qu, Jingxiang He, Shengfeng Ren, Wenqi Hoang, Trung Zhang, Haichuan Yazdani, Amirsaeed Monga, Vishal Yang, Lehan Wu, Alex Jiahao Mai, Tiancheng Cong, Xiaofeng Yin, Xuemeng Yin, Xuefei Emad, Hazim Abdallah, Ahmed Yasser, Yahya Elshahat, Dalia Elbaz, Esraa Li, Zhan Kuang, Wenqing Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Zhang, Zhao Wei, Yanyan Wang, Junhu Zhao, Suiyi Zheng, Huan Guo, Jin Sun, Yangfan Liu, Tianli Hao, Dejun Jiang, Kui Sarvaiya, Anjali Prajapati, Kalpesh Patra, Ratnadeep Barik, Pragnesh Rathod, Chaitanya Upla, Kishor Raja, Kiran Ramachandra, Raghavendra Busch, Christoph ETcTI Universitatea Politehnica Timisoara Romania ICTEAM UCL Belgium Computer Vision Lab University of Wuerzburg Germany Computer Vision Lab ETH Zurich Switzerland Department of Electrical and Computer Engineering McMaster University Canada Department of Electrical and Computer Engineering University of Alberta Canada McMaster University Canada Xidian University China Research Institute Singapore National University of Singapore Singapore University of Sydney Australia Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh12435 Saudi Arabia Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Wuhan University of Technology China Singapore Management University Singapore Singapore Sun Yat-sen University China Electrical Engineering Department Pennsylvania State University United States The University of Sydney Australia Southeast University China University of California Los Angeles United States Beijing Jiaotong University China Mansoura Univeristy Egypt College of Information Science and Technology Jinan University China Department of Information Technology Uppsala University Sweden Hefei University of Technology China Zhejiang Dahua Technology China Sardar Vallabhbhai National Institute of Technology India Norwegian University of Science and Technology Norway

ISBN: (纸本)9798350302493

This study assesses the outcomes of the NTIRE 2023 Challenge on Non-Homogeneous Dehazing, wherein novel techniques were proposed and evaluated on new image dataset called HD-NH-HAZE. The HD-NH-HAZE dataset contains 50 high resolution pairs of real-life outdoor images featuring nonhomogeneous hazy images and corresponding haze-free images of the same scene. The nonhomogeneous haze was simulated using a professional setup that replicated real-world conditions of hazy scenarios. The competition had 246 participants and 17 teams submitted solutions for the final testing phase. The proposed solutions demonstrated the cutting-edge in image dehazing technology. © 2023 IEEE.

关键词： Demulsification

MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hao, Xiaoshuai Li, Ruikai Zhang, Hui Li, Dingzhe Yin, Rong Jung, Sangil Park, Seung-In Yoo, ByungIn Zhao, Haimei Zhang, Jing Samsung R&D Institute China Beijing China State Key Lab of Intelligent Transportation System Beihang University China Institute of Information Engineering Chinese Academy of Sciences China Computer Vision TU SAIT SEC Korea Republic of The University of Sydney Australia

Online high-definition (HD) map construction is an important and challenging task in autonomous driving. Recently, there has been a growing interest in cost-effective multi-view camera-based methods without relying on other sensors like LiDAR. However, these methods suffer from a lack of explicit depth information, necessitating the use of large models to achieve satisfactory performance. To address this, we employ the Knowledge Distillation (KD) idea for efficient HD map construction for the first time and introduce a novel KD-based approach called MapDistill to transfer knowledge from a high-performance camera-LiDAR fusion model to a lightweight camera-only model. Specifically, we adopt the teacher-student architecture, i.e., a camera-LiDAR fusion model as the teacher and a lightweight camera model as the student, and devise a dual BEV transform module to facilitate cross-modal knowledge distillation while maintaining cost-effective camera-only deployment. Additionally, we present a comprehensive distillation scheme encompassing cross-modal relation distillation, dual-level feature distillation, and map head distillation. This approach alleviates knowledge transfer challenges between modalities, enabling the student model to learn improved feature representations for HD map construction. Experimental results on the challenging nuScenes dataset demonstrate the effectiveness of MapDistill, surpassing existing competitors by over 7.7 mAP or 4.5× speedup. Copyright © 2024, The Authors. All rights reserved.

关键词： Cost effectiveness

Discwise Active Learning for LiDAR Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Unal, Ozan Dai, Dengxin Unal, Ali Tamer Van Gool, Luc Computer Vision Lab ETH Zurich Switzerland Huawei Technologies Zurich Research Center Switzerland Department of Industrial Engineering Boğaziçi University Turkey VISICS ESAT/PSI KU Leuven Belgium INSAIT Sofia Bulgaria

While LiDAR data acquisition is easy, labeling for semantic segmentation remains highly time consuming and must therefore be done selectively. Active learning (AL) provides a solution that can iteratively and intelligently label a dataset while retaining high performance and a low budget. In this work we explore AL for LiDAR semantic segmentation. As a human expert is a component of the pipeline, a practical framework must consider common labeling techniques such as sequential labeling that drastically improve annotation times. We therefore propose a discwise approach (DiAL), where in each iteration, we query the region a single frame covers on global coordinates, labeling all frames simultaneously. We then tackle the two major challenges that emerge with discwise AL. Firstly we devise a new acquisition function that takes 3D point density changes into consideration which arise due to location changes or ego-vehicle motion. Next we solve a mixed-integer linear program that provides a general solution to the selection of multiple frames while taking into consideration the possibilities of disc intersections. Finally we propose a semi-supervised learning approach to utilize all frames within our dataset and improve performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

Efficacy of radiomics and genomics in predicting TP53 mutations in diffuse lower grade glioma

学校读者我要写书评

暂无评论

Efficacy of radiomics and genomics in predicting TP53 mutati...

Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging

作者： Shboul, Zeina A. Iftekharuddin, Khan M. Vision Lab in the Department of Electrical and Computer Engineering Old Dominion University NorfolkVA23529 United States

ISBN: (纸本)9781510634015

An updated classification of diffuse lower-grade gliomas is established in the 2016 World Health Organization Classification of Tumors of the Central Nervous System based on their molecular mutations such as TP53 mutation. This study investigates machine learning methods for TP53 mutation status prediction and classification using radiomics and genomics features, respectively. Radiomics features represent patients' age and imaging features that are extracted from conventional MRI. Genomics feature is represented by patients' gene expression using RNA sequencing. This study uses a total of 105 LGG patients, where the patient dataset is divided into a training set (80 patients) and testing set (25 patients). Three TP53 mutation prediction models are constructed based on the source of the training features;TP53-radiomics model, TP53-genomics model, and TP53-radiogenomics model, respectively. Radiomics feature selection is performed using recursive feature selection method. For genomics data, EdgeR method is utilized to select the differentially expressed genes between the mutated TP53 versus the non-mutated TP53 cases in the training set. The training classification model is constructed using Random Forest and cross-validated using repeated 10-fold cross validation. Finally, the predictive performance of the three models is assessed using the testing set. The three models, TP53-Radiomics, TP53-RadioGenomics, and TP53-Genomics, achieve a predictive accuracy of 0.84±0.04, 0.92±0.04, and 0.89±0.07, respectively. These results show promise of non-invasive MRI radiomics features and fusion of radiomics with genomics features for prediction of TP53. © 2020 SPIE

关键词： Genome