云南高校图书馆联盟文献共享服务平台- STEREO

STEREO_MATCHING: 作品数：35被引量：50H指数：4; 导出分析报告; 相关作者：陈鉴富张丽艳王宏涛张辉林国余更多>>; 相关机构：南京航空航天大学东南大学南京信息工程大学哈尔滨工程大学更多>>; 相关期刊：更多>>; 相关基金：国家自然科学基金国家高技术研究发展计划国家教育部博士点基金广东省自然科学基金更多>>

Adaptive Recurrent Iterative Updating Stereo Matching Network: 《Journal of Computer and Communications》2023年第3期83-98,共16页Qun Kong Liye Zhang Zhuang Wang Mingkai Qi Yegang Li; When training a stereo matching network with a single training dataset, the network may overly rely on the learned features of the single training dataset due to differences in the training dataset scenes, resulting i...; 关键词：Stereo Matching Whitening Loss Feature Consistency Convolutional Neural Network GRU

Multilevel Disparity Reconstruction Network for Real-Time Stereo Matching被引量：1: 《Journal of Shanghai Jiaotong university(Science)》2022年第5期715-722,共8页LIU Zhuoran ZHAO Xu; Recently,stereo matching algorithms based on end-to-end convolutional neural networks achieve excellent performance far exceeding traditional algorithms.Current state-of-the-art stereo matching networks mostly rely on...; 关键词：stereo matching disparity reconstruction REAL-TIME stacked residual pyramid

Homography-guided stereo matching for wide-baseline image interpolation被引量：1: 《Computational Visual Media》2022年第1期119-133,共15页Yuan Chang Congyi Zhang Yisong Chen Guoping Wang; supported by the National Key Technology Research and Development Program of China(No.2017YFB1002601);PKU-Baidu Fund(No.2019BD007);National Natural Science Foundation of China(NSFC)(No.61632003).; Image interpolation has a wide range of applications such as frame rate-up conversion and free viewpoint TV.Despite significant progresses,it remains an open challenge especially for image pairs with large displacemen...; 关键词：image interpolation view synthesis homo-graphy propagation belief propagation

Three-dimensional face point cloud hole-filling algorithm based on binocular stereo matching and a B-spline: 《Frontiers of Information Technology & Electronic Engineering》2022年第3期398-408,共11页Yuan HUANG Feipeng DA; supported by the National Natural Science Foundation of China(No.61405034);the Special Project on Basic Research of Frontier Leading Technology of Jiangsu Province,China(No.BK20192004C);the Shenzhen Science and Technology Innovation Committee(No.JCYJ20180306174455080);the Natural Science Foundation of Jiangsu Province,China(No.BK20181269)。; When obtaining three-dimensional(3D)face point cloud data based on structured light,factors related to the environment,occlusion,and illumination intensity lead to holes in the collected data,which affect subsequent r...; 关键词：Three-dimensional(3D)point cloud Hole filling Stereo matching B-SPLINE

Dense 3D surface reconstruction of large-scale streetscape from vehicle-borne imagery and LiDAR: 《International Journal of Digital Earth》2021年第5期619-639,共21页Xiaohu Lin Bisheng Yang Fuhong Wang Jianping Li Xiqi Wang; funded by the National Natural Science Foundation of China for Distinguished Young Scholars[grant number 41725005];the Key Project of the National Natural Science Foundation of China[grant number 41531177];the National Key Research and Development Program of China[grant number 2016YFB0501803].; Accurate and efficient three-dimensional(3D)streetscape reconstruction is the fundamental ability for an exploration vehicle to navigate safely and perform high-level tasks.Recently,remarkable progress has been made i...; 关键词：Dense 3D streetscape reconstruction vehicleborne imagery stereo matching pose estimation multiple filtering

Stereo Matching Method Based on Space-Aware Network Model被引量：1: 《Computer Modeling in Engineering & Sciences》2021年第4期175-189,共15页Jilong Bian Jinfeng Li; This work was supported in part by the Heilongjiang Provincial Natural Science Foundation of China under Grant F2018002;the Research Funds for the Central Universities under Grants 2572016BB11 and 2572016BB12;the Foundation of Heilongjiang Education Department under Grant 1354MSYYB003.; The stereo matching method based on a space-aware network is proposed, which divides the network into threesections: Basic layer, scale layer, and decision layer. This division is beneficial to integrate residue netwo...; 关键词：Deep learning stereo matching space-aware network hybrid loss

Hybrid tree guided PatchMatch and quantizing acceleration for multiple views disparity estimation: 《中国体视学与图像分析》2021年第1期47-61,共15页张吉光徐士彪张晓鹏; 国家重点研究发展计划(No.2018YFB2100602);国家自然科学基金(No.6162010603,91646207,61971418,61771026,61972459)。; Existing stereo matching methods cannot guarantee both the computational accuracy and efficiency for ihe disparity estimation of large-scale or multi-view images.Hybrid tree method can obtain a disparity estimation fa...; 关键词：stereo matching multiple views disparity estimation hybrid tree PatchMatch

A deep learning-based binocular perception system被引量：1: 《Journal of Systems Engineering and Electronics》2021年第1期7-20,共14页SUN Zhao MA Chao WANG Liang MENG Ran PEI Shanshan; supported by the National Natural Science Foundation of China(61673381);the National Key R&D Program of China(2018AAA0103103);the Science and Technology Development Fund(0024/2018/A1)。; An obstacle perception system for intelligent vehicle is proposed.The proposed system combines the stereo version technique and the deep learning network model,and is applied to obstacle perception tasks in complex en...; 关键词：intelligent vehicle stereo matching deep learning environment perception

Robust statistical approach to stereo disparity maps denoising and refinement被引量：2: 《Control Theory and Technology》2020年第4期348-361,共14页James Okae Juan Du Yueming Hu; the 2020 Guangdong International Cooperation Project(No.2019A050510007).; The advent of convolutional neural networks has led to remarkable progress in dense stereo labeling problem,achieving superior performance over the traditional methods.However,the ill-posed nature of stereo matching m...; 关键词：Stereo matching Disparity enhancement Robust statistics Markov random field

InStereo2K:a large real dataset for stereo matching in indoor scenes被引量：8: 《Science China(Information Sciences)》2020年第11期128-138,共11页Wei BAO Wei WANG Yuhua XU Yulan GUO Siyu HONG Xiaohu ZHANG; supported by National Natural Science Foundation of China(Grant Nos.61402489,61972435,61972435,61602499);Natural Science Foundation of Guangdong Province(Grant No.2019A1515011271);Fundamental Research Funds for the Central Universities(Grant No.18lgzd06);Shenzhen Technology and Innovation Committee(Grant No.201908073000399)。; Deep neural networks have shown great success in stereo matching in recent years.On the KITTI datasets,most top performing methods are based on neural networks.However,on the Middlebury datasets,these methods usually ...; 关键词：stereo matching depth estimation convolutional neural network DATASET

STEREO_MATCHING