Biography

I am currently a software engineer at an autonomous driving company Moonx. My major work focus on Perception and Prediction module using deep learning techniques. I did my PhD at Team TITANE of INRIA Sophia-Antipolis in the filed of 3D Computer Vision and Computer Graphics advised by Florent LAFARGE. Before that, I received my master and bachelor degree of Beihang University. As well, I spent the last year of the Engineer Program at Ecole Centrale Paris majored in Applied Mathematics.

My research interest mainly lies in 3D Computer Vision and geometric modeling, which include semantic segmentation, shape detection, surface reconstruction using optimization-based and deep learning methods.

Research Projects

Planar Shape Detection at Structural Scales. Fang H., Lafarge F. and Desbrun M. Proc. of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2018. [paper][bibtex]

Pyramid Scene Parsing Network in 3D: improving semantic segmentation of point clouds with multi-scale contextual information. Fang H., Lafarge F. ISPRS Journal of Photogrammetry and Remote Sensing (JPRS), Vol. 154, 2019. [paper][bibtex][project]

Connect-and-Slice: an hybrid approach for reconstructing 3D objects. Fang H., Lafarge F. Proc. of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2020. [paper][bibtex]