2023-12-02-lian23a.md

title	section	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking	Poster	44FPaVRWkbl	Recent multi-camera 3D object detectors usually leverage temporal information to construct multi-view stereo that alleviates the ill-posed depth estimation. However, they typically assume all the objects are static and directly aggregate features across frames. This work begins with a theoretical and empirical analysis to reveal that ignoring the motion of moving objects can result in serious localization bias. Therefore, we propose to model Dynamic Objects in RecurrenT (DORT) to tackle this problem. In contrast to previous global BirdEye-View (BEV) methods, DORT extracts object-wise local volumes for motion estimation that also alleviates the heavy computational burden. By iteratively refining the estimated object motion and location, the preceding features can be precisely aggregated to the current frame to mitigate the aforementioned adverse effects. The simple framework has two significant appealing properties. It is flexible and practical that can be plugged into most camera-based 3D object detectors. As there are predictions of object motion in the loop, it can easily track objects across frames according to their nearest center distances. Without bells and whistles, DORT outperforms all the previous methods on the nuScenes detection and tracking benchmarks with $62.8%$ NDS and $57.6%$ AMOTA, respectively. The source code will be available at https://github.com/OpenRobotLab/DORT.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	lian23a	0	DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking	3749	3765	3749-3765	3749	false	LIAN, Qing and Wang, Tai and Lin, Dahua and Pang, Jiangmiao	given family Qing LIAN given family Tai Wang given family Dahua Lin given family Jiangmiao Pang	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/lian23a/lian23a.pdf