Zan Gojcic


I am a final year PhD student at ETH Zurich advised by Andreas Wieser and Jan D. Wegner. My research interests are focused around 3D deep learning, weakly supervised learning, and representation learning for tasks such as point cloud registration, scene flow estimation, and scene understanding. Previously, I have visited the geometric computation group led by Leonidas Guibas at Stanford University, where I had the opportunity to work with Tolga Birdal and Srinath Sridhar. Currently, I am interning as a research scientist at NVIDIA AI Lab under supervision of Or Litany and Sanja Fidler. Outside of research I enjoy travelling, playing soccer, cooking, and spending quality time with my friends.

Email: zan dot gojcic at gmail dot com



News


Publications


Weakly Supervised Learning of Rigid 3D Scene Flow
Zan Gojcic, Or Litany, Andreas Wieser, Leonidas Guibas, Tolga Birdal
Computer Vision and Pattern Recognition (CVPR), 2021
Oral Presentation
PDF / Code / Project page


PREDATOR: Registration of 3D Point Clouds with Low Overlap
Shengyu Huang*, Zan Gojcic*, Mikhail Usvyatsov, Andreas Wieser, Konrad Schindler
Computer Vision and Pattern Recognition (CVPR), 2021
Oral Presentation
PDF / Code / Project page


CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
Davis Rempe, Tolga Birdal, Yongheng Zhao, Zan Gojcic, Srinath Sridhar, Leonidas Guibas
Neural Information Processing Systems (NeurIPS), 2020
Spotlight Presentation
PDF / Code / Project page


Learning Multiview 3D Point Cloud Registration
Zan Gojcic*, Caifa Zhou*, Jan D. Wegner, Leonidas Guibas, Tolga Birdal
Computer Vision and Pattern Recognition (CVPR), 2020
PDF / Code


The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
Zan Gojcic, Caifa Zhou, Jan D. Wegner, Andreas Wieser
Computer Vision and Pattern Recognition (CVPR), 2019
PDF / Code


Machine learning and geodesy: a survey
Jemil Butt, Andreas Wieser, Zan Gojcic, Caifa Zhou
Journal of Applied Geodesy, 2021
PDF


(*) Denotes equal contributions.