About Me

My name is Zixuan Huang (pronounced as Zi-Shwan Hwung), currently a first-year PhD student working with Professor Jim Rehg at Georgia Institute of Technology. I got my masters degree at University of Wisconsin-Madison, where I was fortunate to work with Professor Yin Li. I received my B.E. in the Special Class for Gifted Young from University of Science and Technology of China (USTC) in 2018, supervised by Professor Nenghai Yu.

During my undergrad, I also collaborated with Professor Hongsheng Li and Dr. Shuai Yi at Sensetime, exploring several interesting research ideas there.

Research Interest

My primary research interest is computer vision, with a focus on weakly supervised learning and 3D shape reconstruction. By inducing priors that humans utilize into deep neural networks, I hope to understand the learning of our deep models better and to enable the models to understand visual data with minimal human supervision.


Interpretable and Accurate Fine-grained Recognition via Region Grouping
Zixuan Huang, Yin Li
IEEE Conference on Computer Vision and Pattern Recognition (CVPR, oral presentation), 2020.
[arXiv] [code] [project] [slides] [video]

HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion
Zixuan Huang, Junming Fan, Shenggan Cheng, Shuai Yi, Xiaogang Wang, Hongsheng Li
IEEE Trans. on Image Processing (TIP), 2019.