Dr. Tao Hu       胡濤博士

School of Computing
National University of Singapore (NUS)

Email 1: taohu AT NUS DOT EDU DOT SG
Email 2: yihouxiang AT gmail DOT com


Biography [CV]

I am currently a Research Manager (Post-Doctor) in National University of Singapore (NUS), School of Computing, in which I am working with Prof. Gim Hee Lee in 3D Computer Vision. Before that, I received the Doctor's Degree at Computer Science & Engineering Department, The Chinese University of Hong Kong (CUHK), under the supervision of Prof. Jiaya Jia. I obtained the Master degree in Computer Science, University of Chinese Academy of Sciences (UCAS) in 2019, supervised by Prof. Honggang Qi. I received the Bachelor degree in Automation Engineering from University of Electronic Science and Technology of China (UESTC) in 2016.

Recently, I founded RealityEdge which combines Large Model with Interaction for creative work.

My current research interests includes primarily in 3D Computer Vision and Graphics, particularly focusing on:

Neural Radiance Fields (NeRF), 2D image / 3D Scene Synthesis, 3D Rendering and Reconstruction.

Recent News

May, 2024 X-Ray: We released a novel representation for 3D Generation from text or image !
Match, 2024 One paper was accepted in CVPR-2024.
October, 2023 Ref-NeuS: Our paper was selected as the Best Paper Candidates !
July, 2023 Ref-NeuS: One Oral paper was accepted by ICCV-2023 about 3D Object Reconstruction!
April, 2023 ReTryOn: We released the application of Virtual TryOn within 10 seconds!
March, 2023RealityComposition: We released the source code of compositing images via Stable Diffusion!
March, 2023 CVPR-2023: Our three papers were accepted by CVPR-2023!

Selected Publications [Google Scholar]

X-Ray: A Sequential 3D Representation for Generation.
Tao Hu, Wenhang Ge, Yuyang Zhao, Gim Hee Lee.
Arxiv Poster
Boosting Image Restoration via Priors from Pre-trained Models.
Xiaogang Xu, Shu Kong, Tao Hu, Zhe Liu, Hujun Bao.
CVPR-2024 Poster
Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection.
Wenhang Ge, Tao Hu, Haoyu Zhao, Shu Liu, Ying-Cong Chen.
ICCV-2023 Oral + Best Paper Candidate
TriVol: Point Cloud Rendering via Triple Volumes.
Tao Hu, Xiaogang Xu, Ruihang Chu, Jiaya Jia.
Point2Pix: Photo-Realistic Point Cloud Rendering
via Neural Radiance Fields.
Tao Hu, Xiaogang Xu, Shu Liu, Jiaya.
NeRFLix: High-Quality Neural View Synthesis by
Learning a Degradation-Driven Inter-viewpoint MiXer.
Zhou Kun, Wenbo Li, Yi Wang, Tao Hu, Nianjuan Jiang,
Xiaoguang Han, Jiangbo Lu.
EfficientNeRF: Efficient Neural Radiance Fields.
Tao Hu, Shu Liu, Yilun Chen, Tianchen Shen, Jiaya Jia.
Self-Supervised 3D Mesh Reconstruction from Single Images.
Tao Hu, Liwei Wang, Xiaogang Xu, Shu Liu, Jiaya Jia.
See better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification.
Tao Hu, Honggang Qi, Qingming Huang, Yu Lu.
Weakly Supervised Local Attention Network for Fine-Grained Visual Classification.
Tao Hu, Honggang Qi , Cong Huang , Qingming Huang ,Yan Lu ,Jizheng Xu.
Facial landmarks detection by self-iterative regression based landmarks-attention network.
Tao Hu, Honggang Qi, Jizheng Xu, Qingming Huang.
UA-DETRAC 2017: Report of AVSS2017 & IWT4S challenge on advanced traffic monitoring.
Siwei Lyu, Ming-Ching Chang, Dawei Du, Longyin Wen, Honggang Qi, Yuezun Li, Yi Wei, Lipeng Ke, Tao Hu, Marco Del Coco..


Honors and Awards

Professional Services

  • Conference Services:
    European Conference on Computer Vision (ECCV’24)
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR’20-24)
    IEEE International Conference on Computer Vision (ICCV’19,21)
    European Conference on Computer Vision (ECCV’20)

  • Journal Reviews:

  • Teaching

    2021-2022SpringENGG5104: Image Processing and Computer Vision
    2019-2020FallCSCI1130: Introduction to Computing Using Java
    2019-2020SpringCSCI3310: Mobile Computing and Applications Development
    © Tao Hu | Last updated: April 2024