BANet: Bilateral Aggregation Network for Mobile Stereo Matching

Authors: Xu, Gangwei, Liu, Jiaxin, Wang, Xianqi, Cheng, Junda, Deng, Yong, Zang, Jinliang, Chen, Yurui, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2503.03259

BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation

Authors: Xu, Gangwei, Lin, Haotong, Zhang, Zhaoxing, Luo, Hongcheng, Sun, Haiyang, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2503.03256

ZeroStereo: Zero-shot Stereo Matching from Single Images

Authors: Wang, Xianqi, Yang, Hao, Xu, Gangwei, Cheng, Junda, Lin, Min, Deng, Yong, Zang, Jinliang, Chen, Yurui, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2501.08654

MonSter: Marry Monodepth to Stereo Unleashes Power

Authors: Cheng, Junda, Liu, Longliang, Xu, Gangwei, Wang, Xianqi, Zhang, Zhaoxing, Deng, Yong, Zang, Jinliang, Chen, Yurui, Cai, Zhipeng, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2501.08643

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation

Authors: Lin, Min, Xu, Gangwei, Wang, Yun, Wang, Xianqi, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2412.17366

Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry

Authors: Zhang, Zhaoxing, Cheng, Junda, Xu, Gangwei, Wang, Xiaoxiang, Zhang, Can, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2412.16923

Event-assisted 12-stop HDR Imaging of Dynamic Scene

Authors: Guo, Shi, Chen, Zixuan, Zhang, Ziran, Chen, Yutian, Xu, Gangwei, Xue, Tianfan

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2412.14705

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions

Authors: Xu, Gangwei, Wang, Yujin, Gu, Jinwei, Xue, Tianfan, Yang, Xin

Source: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) CVPR Computer Vision and Pattern Recognition (CVPR), 2024 IEEE/CVF Conference on. :24851-24860 Jun, 2024

Relation: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching

Authors: Wang, Xianqi, xu, Gangwei, Jia, Hao, Yang, Xin

Source: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) CVPR Computer Vision and Pattern Recognition (CVPR), 2024 IEEE/CVF Conference on. :19701-19710 Jun, 2024

Relation: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

MC-Stereo: Multi-Peak Lookup and Cascade Search Range for Stereo Matching

Authors: Feng, Miaojie, Cheng, Junda, Jia, Hao, Liu, Longliang, Xu, Gangwei, Yang, Xin

Source: 2024 International Conference on 3D Vision (3DV) 3DV 3D Vision (3DV), 2024 International Conference on. :344-353 Mar, 2024

Relation: 2024 International Conference on 3D Vision (3DV)

Hybrid Cost Volume for Memory-Efficient Optical Flow

Authors: Zhao, Yang, Xu, Gangwei, Wu, Gang

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2409.04243

IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching

Authors: Xu, Gangwei, Wang, Xianqi, Zhang, Zhaoxing, Cheng, Junda, Liao, Chunyuan, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2409.00638

Iterative Geometry Encoding Volume for Stereo Matching

Authors: Xu, Gangwei, Wang, Xianqi, Ding, Xiaohuan, Yang, Xin

Source: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) CVPR Computer Vision and Pattern Recognition (CVPR), 2023 IEEE/CVF Conference on. :21919-21928 Jun, 2023

Relation: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation

Authors: Feng, Miaojie, Liu, Longliang, Jia, Hao, Xu, Gangwei, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2312.16995

Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume

Authors: Xu, Gangwei, Chen, Shujun, Jia, Hao, Feng, Miaojie, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2312.03790

MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching

Authors: Feng, Miaojie, Cheng, Junda, Jia, Hao, Liu, Longliang, Xu, Gangwei, Hu, Qingyong, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2311.02340

Attention Concatenation Volume for Accurate and Efficient Stereo Matching

Authors: Xu, Gangwei, Cheng, Junda, Guo, Peng, Yang, Xin

Source: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) CVPR Computer Vision and Pattern Recognition (CVPR), 2022 IEEE/CVF Conference on. :12971-12980 Jun, 2022

Relation: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction

Authors: Xu, Gangwei, Zhou, Huan, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2301.02789

Accurate and Efficient Stereo Matching via Attention Concatenation Volume

Authors: Xu, Gangwei, Wang, Yun, Cheng, Junda, Tang, Jinhui, Yang, Xin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2209.12699

Coatrsnet: Fully Exploiting Convolution and Attention for Stereo Matching by Region Separation.

Authors: Cheng, Junda¹ (AUTHOR), Xu, Gangwei¹ (AUTHOR), Guo, Peng¹ (AUTHOR), Yang, Xin¹ (AUTHOR) xinyang2014@hust.edu.cn

Source: International Journal of Computer Vision. Jan2024, Vol. 132 Issue 1, p56-73. 18p.

Subject Terms: *CONVOLUTIONAL neural networks, *FEATURE extraction