Zixin, LUO

Ph.D. Student

(Email) zluoag[at]cse[dot]ust[dot]hk
Last update 07/2019

About Me

I'm a Ph.D. student (2016-) of Computer Science and Engineering at HKUST, advised by Prof. Long Quan. Prior to HKUST, I studied Automation as an undergraduate at Tsinghua University, where I received my B.Eng. in 2016. Besides, I spent time at UPenn with Dr. Hyun Soo Park (now Prof.) and Prof. Jianbo Shi in 2015, also in SenseTime Group with Mr. Xudong Cao during 2015-2016.
My research interests lie on Computer Vision, and in particular on matching problems in 3D vision, aiming to bridge 2D and 3D with geometry and learning, meanwhile keeping methods practical. I'm also a developer of Altizure on a 3D reconstruction platform.

Publications

2019

• Learning Two-View Correspondences and Geometry Using Order-Aware Network [comming soon]

   Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Hongen Liao, Long Quan

    International Conference on Computer Vision (ICCV), 2019

• ContextDesc: Local Descriptor Augmentation with Cross-Modality Context [arxiv] [code]

   Zixin Luo, Tianwei Shen, Lei Zhou, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, Long Quan

    Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [oral presentation]

• Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference [arxiv] [code]

   Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan

    Conference on Computer Vision and Pattern Recognition (CVPR), 2019

• Cross-atlas Convolution for Parameterization Invariant Learning on Textured Mesh Surface [pdf]

   Shiwei Li, Zixin Luo, Mingmin Zhen, Yao Yao, Tianwei Shen, Tian Fang, Long Quan

    Conference on Computer Vision and Pattern Recognition (CVPR), 2019

• Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation [arxiv] [code]

   Tianwei Shen, Zixin Luo, Lei Zhou, Hanyu Deng, Runze Zhang, Tian Fang, Long Quan

    International Conference on Robotics and Automation (ICRA), 2019

2018

• Matchable Image Retrieval by Learning from Surface Reconstruction [arxiv] [code]

   Zixin Luo*, Tianwei Shen*, Lei Zhou, Runze Zhang, Siyu Zhu, Tian Fang, Long Quan

   (* indicates equal contribution)

   Asian Conference on Computer Vision (ACCV), 2018

• GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints [paper] [arxiv] [bibtex] [poster] [code]

   Zixin Luo, Tianwei Shen, Lei Zhou, Siyu Zhu, Runze Zhang, Yao Yao, Tian Fang, Long Quan

   European Conference on Computer Vision (ECCV), 2018

•  MVSNet: Depth Inference for Unstructured Multi-view Stereo [arxiv] [supp] [code]

   Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, Long Quan

   European Conference on Computer Vision (ECCV), 2018 [oral presentation]

•  Learning and Matching Multi-View Descriptors for Registration of Point Clouds [arxiv] [code]

   Lei Zhou, Siyu Zhu, Zixin Luo, Tianwei Shen, Runze Zhang, Mingmin Zhen, Tian Fang, Long Quan

   European Conference on Computer Vision (ECCV), 2018

•  Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus [pdf]

   Runze Zhang, Siyu Zhu, Tianwei Shen, Lei Zhou, Zixin Luo, Tian Fang, Long Quan

   IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2018