Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Andrew G. Berneshawi, Huimin Ma, Sanja Fidler, Raquel Urtasun. 3D Object Proposals for Accurate Object Class Detection. NIPS, 2015.

Chen et al. present a 3d object proposal detector which operates directly in point clouds and is shown to outperform related approaches. In experiments they use the proposal detector to improve the performance of a R-CNN based detector and demonstrate improved performance.

What is your opinion on the summarized work? Or do you know related work that is of interest? Let me know your thoughts in the comments below: