Haozhe Xie
Research Fellow at MMLab@NTU
School of Computer Science and Engineering
Nanyang Technological University
Email: root [at] haozhexie [dot] com
GitHub | Google Scholar | Curriculum Vitae
Biography
I am currently working as a research fellow at MMLab@NTU, Nanyang Technological University, under the supervision of Prof. Ziwei Liu. Prior to this, I served as a senior research scientist (2021-2023) at Tencent AI Lab.
I completed my Ph.D. degree (2017-2021) at the VILab of Harbin Institute of Technology, under the guidance of Prof. Hongxun Yao. During my Ph.D. study, I interned at SenseTime Research.
My research interests include computer vision and deep learning with a focus on 3D generation and reconstruction.
Publications
- Huicong Zhang, Haozhe Xie, Hongxun Yao. Spatio-Temporal Deformable Attention Network for Video Deblurring. ECCV, 2022.[BibTeX] [PDF] [Project Page]
@inproceedings{zhang2022spatio, title={Spatio-Temporal Deformable Attention Network for Video Deblurring}, author={Zhang, Huicong and Xie, Haozhe and Yao, Hongxun}, booktitle={ECCV}, year={2022} }
- Xiaoqian Lv, Shengping Zhang, Qinglin Liu, Haozhe Xie, Bineng Zhong, Huiyu Zhou. BacklitNet: A dataset and network for backlit image enhancement. Computer Vision and Image Understanding, 218: 103403, 2022. (IF=3.876)[BibTeX] [PDF] [Dataset]
@article{lv2022backlitnet, title={BacklitNet: A dataset and network for backlit image enhancement}, author={Lv, Xiaoqian and Zhang, Shengping and Liu, Qinglin and Xie, Haozhe and Zhong, Bineng and Zhou, Huiyu}, journal={Computer Vision and Image Understanding}, year={2022}, volume={218}, pages={103403}, doi={10.1016/j.cviu.2022.103403} }
- Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Xiaojun Tong, Wenxiu Sun. Toward 3D Object Reconstruction from Stereo Images. Neurocomputing, 463: 444-453, 2021. (IF=5.719)[BibTeX] [PDF] [Project Page]
@article{xie2021toward, title={Toward 3D Object Reconstruction from Stereo Images}, author={Xie, Haozhe and Yao, Hongxun and Zhou, Shangchen and Zhang, Shengping and Tong, Xiaojun and Sun, Wenxiu}, journal={Neurocomputing}, year={2021}, volume={463}, pages={444--453}, doi={10.1016/j.neucom.2021.07.089} }
- Qinglin Liu, Haozhe Xie, Shengping Zhang, Bineng Zhong, Rongrong Ji. Long-Range Feature Propagating for Natural Image Matting. ACM Multimedia, 2021.
- Haozhe Xie. 3D Scene and Object Reconstruction from Multiple Sources and Viewpoints. PhD thesis, Harbin Institute of Technology, 2021.
- Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Wenxiu Sun. Efficient Regional Memory Network for Video Object Segmentation. CVPR, 2021.[BibTeX] [PDF] [Project Page]
@inproceedings{xie2021efficient, title={Efficient Regional Memory Network for Video Object Segmentation}, author={Xie, Haozhe and Yao, Hongxun and Zhou, Shangchen and Zhang, Shengping and Sun, Wenxiu}, booktitle={CVPR}, year={2021} }
- Shuo Yang, Min Xu, Haozhe Xie, Stuart Perry, Jiahao Xia. Single-View 3D Object Reconstruction from Shape Priors in Memory. CVPR, 2021.
- Haozhe Xie, Hongxun Yao, Shangchen Zhou, Jiageng Mao, Shengping Zhang, Wenxiu Sun. GRNet: Gridding Residual Network for Dense Point Cloud Completion. ECCV, 2020.[BibTeX] [PDF] [Project Page]
@inproceedings{xie2020grnet, title={GRNet: Gridding Residual Network for Dense Point Cloud Completion}, author={Xie, Haozhe and Yao, Hongxun and Zhou, Shangchen and Mao, Jiageng and Zhang, Shengping and Sun, Wenxiu}, booktitle={ECCV}, year={2020} }
- Haozhe Xie, Hongxun Yao, Shengping Zhang, Shangchen Zhou, Wenxiu Sun. Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images. International Journal of Computer Vision (IJCV), 128(12): 2919-2935, 2020. (IF=7.410)[BibTeX] [PDF]
@article{xie2020pix2vox++, title={Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images}, author={Xie, Haozhe and Yao, Hongxun and Zhang, Shengping and Zhou, Shangchen and Sun, Wenxiu}, journal={International Journal of Computer Vision (IJCV)}, year={2020}, volume={128}, number={12}, pages={2919--2935}, doi={10.1007/s11263-020-01347-6} }
- Yuzhi Tan, Hongxun Yao, Haoran Li, Xiusheng Lu, Haozhe Xie. PRF-Ped: Multi-scale Pedestrian Detector with Prior-based Receptive Field. ICPR, 2020.
- Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Shengping Zhang. Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images. ICCV, 2019.[BibTeX] [PDF] [Project Page]
@inproceedings{xie2019pix2vox, title={Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images}, author={Xie, Haozhe and Yao, Hongxun and Sun, Xiaoshuai and Zhou, Shangchen and Zhang, Shengping}, booktitle={ICCV}, year={2019} }
- Shangchen Zhou, Jiawei Zhang, Jinshan Pan, Haozhe Xie, Wangmeng Zuo, Jimmy Ren. Spatio-Temporal Filter Adaptive Network for Video Deblurring. ICCV, 2019.[BibTeX] [PDF] [Project Page]
@inproceedings{zhou2019spatio, title={Spatio-Temporal Filter Adaptive Network for Video Deblurring}, author={Zhou, Shangchen and Zhang, Jiawei and Pan, Jinshan and Xie, Haozhe and Zuo, Wangmeng and Ren, Jimmy}, booktitle={ICCV}, year={2019} }
- Shangchen Zhou, Jiawei Zhang, Wangmeng Zuo, Haozhe Xie, Jinshan Pan, Jimmy Ren. DAVANet: Stereo Deblurring with View Aggregation. CVPR, 2019. (Oral)[BibTeX] [PDF] [Project Page] [Dataset]
@inproceedings{zhou2019davanet, title={DAVANet: Stereo Deblurring with View Aggregation}, author={Zhou, Shangchen and Zhang, Jiawei and Zuo, Wangmeng and Xie, Haozhe and Pan, Jinshan and Ren, Jimmy}, booktitle={CVPR}, year={2019} }
- Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Xiaojun Tong. Weighted Voxel: a novel voxel representation for 3D reconstruction. International Conference on Internet Multimedia Computing and Service (ICIMCS), 2018.[BibTeX] [PDF] [Project Page]
@inproceedings{xie2018weighted, title={Weighted Voxel: a novel voxel representation for 3D reconstruction}, author={Xie, Haozhe and Yao, Hongxun and Sun, Xiaoshuai and Zhou, Shangchen and Tong, Xiaojun}, booktitle={International Conference on Internet Multimedia Computing and Service (ICIMCS)}, year={2018}, organization={acm} }
- Hanqing Xue, Jie Li, Haozhe Xie, Yadong Wang. Review of drug repositioning approaches and resources. International Journal of Biological Sciences, 14(10): 1232-1244, 2018. (IF=4.057)
- Haozhe Xie. Research on dimensionality reduction methods based on random projection. Master's thesis, Harbin Institute of Technology, 2017.
- Haozhe Xie, Jie Li, Hanqing Xue. A survey of dimensionality reduction techniques based on random projection. arXiv preprint:1706.04371, 2017.
- Qiaosheng Zhang, Jie Li, Haozhe Xie, Hanqing Xue, Yadong Wang. A network-based pathway-expanding approach for pathway analysis. BMC Bioinformatics, 17: 231-241, 2016. (IF=2.448)
- Haozhe Xie, Jie Li, Qiaosheng Zhang, Yadong Wang. Comparison among dimensionality reduction techniques based on Random Projection for cancer classification. Computational biology and chemistry, 65: 165-172, 2016. (IF=1.331)[BibTeX] [PDF] [Code] [Dataset]
@article{xie2016comparison, title={Comparison among dimensionality reduction techniques based on Random Projection for cancer classification}, author={Xie, Haozhe and Li, Jie and Zhang, Qiaosheng and Wang, Yadong}, journal={Computational biology and chemistry}, year={2016}, volume={65}, pages={165--172} }
Invited Talks
- 3D Object and Scene Reconstruction Meets Neural Networks. Faculty of Computing, Harbin Institute of Technology, Harbin, China. May 2021. [News]
- Deep Learning Fundamentals. Zhejiang Institute of Research and Innovation, The University of Hong Kong, Hangzhou, China. July 2019. [News]
- Computer Fundamentals. Hangzhou No.14 High School, Hangzhou China. August 2014.
- Data Structure. Hangzhou No.14 High School, Hangzhou China. August 2012.
Open Source Contribution
Verwandlung Online Judge
Verwandlung Online Judge is a Spring MVC based online judge system that supports multiple operating systems, including Windows and Linux. Communication between the judgers and web modules takes place through a message queue named ActiveMQ.
[Learn More]
Tiny DNN
TinyDNN is an implementation of deep learning written in C++14, designed to be used on IoT devices with limited computational resources. As part of this project, I implemented transposed convolutional layers and the Single Shot MultiBox Detector (SSD) for object detection.
[Learn More]
XX-Net
XX-Net is a free and open-source desktop application that provides users in censored regions with fast, reliable, and secure access to the open internet. It accomplishes this by using Google App Engine as a proxy server to bypass firewalls and access blocked websites.
[Learn More]
V2Ray Desktop
V2Ray Desktop is a native and cross-platform proxy GUI client written in Qt 5 and QML 2. It supports Shadowsocks(R), V2Ray, and Trojan protocols.
[Learn More]
WordPress Plugin: Google Font Fix
Google Font Fix is a WordPress plugin designed to enhance the page loading speed for Chinese users by replacing Google and Gravatar links with reverse proxy servers located in China.
[Learn More]
WordPress Plugin: WP-BibTeX
WP-BibTeX is a helpful WordPress plugin that simplifies formatting of BibTeX entries to display a bibliography or cite papers in WordPress. It has been used to generate the content of the Publications section on this page.
[Learn More]
Copyright
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
