Tuesday, 1.12.2020, 11:30
Zoom Lecture: https://technion.zoom.us/j/95668947180
In this talk i'll be covering several works in the topic of 3D deep learning on pointclouds for scene understanding tasks.
First, I'll describe VoteNet (ICCV 2019): a method for object detection from 3D pointclouds input, inspired by the classical generalized Hough voting technique. I'll then explain how we integrated image information into the voting scheme to further boost 3D detection (ImVoteNet, CVPR 2020). In the second part of my talk i'll describe a recent study about transfer-learning for 3D pointclouds which led to the development of the PointContrast framework (ECCV 2020). Our findings are extremely encouraging: using a unified triplet of architecture, source dataset, and contrastive loss for pre-training, we achieve improvement over recent best results in segmentation and detection across 6 different benchmarks for indoor and outdoor, real and synthetic datasets -- demonstrating that the learned representation can generalize across domains.
Or Litany (PhD 2018, Tel-Aviv University) is a Research Scientist at Nvidia. Before that he was a postdoctoral fellow at Stanford University, advised by Prof. Leonidas Guibas and a postdoc at Facebook AI Research. Or received his B.Sc. in Physics and Mathematics from the Hebrew University under the auspices of “Talpiot”. He holds an M.Sc. (Magna Cum Laude) and Ph.D. degrees in Electrical Engineering from Tel-Aviv University. During his PhD, Or has held visiting researcher appointments at TU Munich and Duke universities and was a research intern at Microsoft Research, Intel, and Google Research. Or's main interests include 3D deep learning, and methods for reducing supervision. He is the recipient of several awards including the Weinstein prize for graduate studies (2015), a DAAD research grant (2016), a best paper award at SGP'16, best paper runner-up at ICCV'19 and best paper award at ICML'20.