Detail of the student project

Topic:Vylepšení mračen 3D bodů pro hluboké učení vkládáním objektů
Department:Katedra kybernetiky
Supervisor:prof. Ing. Tomáš Svoboda, Ph.D.
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:Design and implement an automatic method for the insertion of new objects into 3D point cloud data. Insertion must correctly handle visibility.
Experimentally verify augmented data on several 3D object detection pipelines (SECOND, PointPillars, PointRCNN,
The contribution of the augmentation steps shall be evaluated by an ablation study.
Bibliography:[1] Martin Hahner, Dengxin Dai, Alexander Liniger, and Luc Van Gool. Quantifying Data Augmentation for LiDAR based 3D Object Detection. arXiv:2004.01643, 1:1–7, 2020.

[2] Jin Fang, Xinxin Zuo, Dingfu Zhou, Shengze Jin, Sen Wang, and Liangjun Zhang. LiDAR-Aug: A General Rendering-based Augmenta- tion Framework for 3D Object Detection. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4708–4718, 2021.

[3] Chunwei Wang, Chao Ma, Ming Zhu, Xiaokang Yang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 11794-11803

[4] Peiyun Hu, Jason Ziglar, David Held, Deva Ramanan. What You See is What You Get: Exploiting Visibility for 3D Object Detection. CVPR 2020

[5] Hu, Jordan SK, and Steven L. Waslander. "Pattern-Aware Data
Augmentation for LiDAR 3D Object Detection." 2021 IEEE International
Intelligent Transportation Systems Conference (ITSC). IEEE, 2021.
Responsible person: Petr Pošík