@inproceedings{fe99a22b8c2a47029b4fd98a5300d229,
title = "Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds",
abstract = "Understanding the flow in 3D space of sparsely sampled points between two consecutive time frames is the core stone of modern geometric-driven systems such as VR/AR,Robotics,and Autonomous driving. The lack of real,non-simulated,labeled data for this task emphasizes the importance of self- or un-supervised deep architectures. This work presents a new self-supervised training method and an architecture for the 3D scene flow estimation under occlusions. Here we show that smart multi-layer fusion between flow prediction and occlusion detection outperforms traditional architectures by a large margin for occluded and non-occluded scenarios. We report state-of-the-art results on Flyingthings3D and KITTI datasets for both the supervised and self-supervised training.1",
author = "Bojun Ouyang and Dan Raviv",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 9th International Conference on 3D Vision, 3DV 2021 ; Conference date: 01-12-2021 Through 03-12-2021",
year = "2021",
doi = "https://doi.org/10.1109/3DV53792.2021.00087",
language = "الإنجليزيّة",
series = "Proceedings - 2021 International Conference on 3D Vision, 3DV 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "782--791",
booktitle = "Proceedings - 2021 International Conference on 3D Vision, 3DV 2021",
address = "الولايات المتّحدة",
}