未来媒体计算实验室

办公地址：中科大高新校区一号学科楼

电子邮箱：qingshan.xu@ustc.edu.cn

个人主页：https://ghixu.github.io/

个人简介

徐青山，中国科学技术大学信息科学技术学院自动化系特任教授，博士生导师，国家级青年人才。2021年博士毕业于华中科技大学，曾在新加坡南洋理工大学担任博士后研究员，访学于苏黎世联邦理工学院计算机视觉与几何（CVG）实验室。主要研究方向为三维视觉、空间智能、物理AI、具身感知等，相关科研成果发表在IEEE Transactions on Pattern Analysis and Machine Intelligence（TPAMI）等国际顶级期刊以及CCF-A类会议上共计30余篇。受邀担任TPAMI, IJCV, TIP, TVCG, CVPR, ICCV, ECCV等多个期刊/会议的审稿人。

研究方向

 三维视觉

 空间智能

 物理AI

 具身感知

代表性论文

[1] Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys. “Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023, 45(4):4945-4963.

[2] Fangjinhua Wang#, Qingshan Xu#, Yew-Soon Ong, Marc Pollefeys. “Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025, 47(11):10060-10075. （共同一作）

[3] Jiaqi Yang, Yanan He, Chunlin Ren, Qingshan Xu*, Siwen Quan, Xiyu Zhang, Yanning Zhang. “A Hierarchical Prior Mining Approach for Non-local Multi-view Stereo”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026. （通讯作者）

[4] Qingshan Xu, Wanjuan Su, Yuhang Qi, Wenbing Tao, Marc Pollefeys. “Learning Inverse Depth Regression for Pixelwise Visibility-Aware Multi-View Stereo Network”. International Journal of Computer Vision (IJCV), 2022，130:2040–2059.

[5] Qingshan Xu, Wenbing Tao. “Multi-Scale Geometric Consistency Guided Multi-View Stereo”. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

[6] Qiancheng Fu#, Qingshan Xu#, Yew-Soon Ong, Wenbing Tao. “Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction”. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022. （共同一作）

[7] Qingshan Xu, Wenbing Tao. “Planar Prior Assisted PatchMatch Multi-View Stereo”. AAAI Conference on Artificial Intelligence (AAAI), 2020.

[8] Qingshan Xu, Wenbing Tao. “Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume”. AAAI Conference on Artificial Intelligence (AAAI), 2020.

[9] Qingshan Xu, Xuanyu Yi, Jianyao Xu, Wenbing Tao, Yew-Soon Ong, Hanwang Zhang. “Few-shot NeRF by Adaptive Rendering Loss Regularization”. European Conference on Computer Vision (ECCV), 2024.

[10] Qingshan Xu#, Jiao Liu#, Shangshu Yu, Yuxuan Wang, Yuan Zhou, Junbao Zhou, Jiequan Cui, Yew-Soon Ong, Hanwang Zhang. “NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos”. AAAI Conference on Artificial Intelligence (AAAI), 2026. （共同一作）