Learning Methods for Robust Spatial Perception

Abstract

From localizing a self-driving vehicle on the street to reconstructing a digital asset through intelligent machines, spatial perception plays a pivotal role to realize these embodied intelligence systems. While several advances in spatial perception have been witnessed over the last decade, perception robustness against adverse conditions (e.g. sensing degradation) remains a challenge. These challenges motivate me to build intelligent systems that realize good spatial perception awareness of the 3D physical world from visual sensory observations. This talk will present our recent contributions to improving the practical robustness of spatial perception against the most common adverse conditions threatening a perception system in the wild.

 

Speaker

Mr Bing WANG is a fourth-year PhD student in the Department of Computer Science at the University of Oxford, supervised by Prof. Niki Trigoni and Prof. Andrew Markham. Prior to studying at Oxford, he obtained a BEng degree from Shenzhen University. His interests broadly lie in spatial perception systems with the goal of drastically improving their reliability, intelligence and security in the wild.