2023-12-02-chen23d.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
Revisiting Depth-guided Methods for Monocular 3D Object Detection by Hierarchical Balanced Depth	Poster	HCWoFkGe8L4	Monocular 3D object detection has seen significant advancements with the incorporation of depth information. However, there remains a considerable performance gap compared to LiDAR-based methods, largely due to inaccurate depth estimation. We argue that this issue stems from the commonly used pixel-wise depth map loss, which inherently creates the imbalance of loss weighting between near and distant objects. To address these challenges, we propose MonoHBD (Monocular Hierarchical Balanced Depth), a comprehensive solution with the hierarchical mechanism. We introduce the Hierarchical Depth Map (HDM) structure that incorporates depth bins and depth offsets to enhance the localization accuracy for objects. Leveraging RoIAlign, our Balanced Depth Extractor (BDE) module captures both scene-level depth relationships and object-specific depth characteristics while considering the geometry properties through the inclusion of camera calibration parameters. Furthermore, we propose a novel depth map loss that regularizes object-level depth features to mitigate imbalanced loss propagation. Our model reaches state-of-the-art results on the KITTI 3D object detection benchmark while supporting real-time detection. Excessive ablation studies are also conducted to prove the efficacy of our proposed modules.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	chen23d	0	Revisiting Depth-guided Methods for Monocular 3D Object Detection by Hierarchical Balanced Depth	2995	3009	2995-3009	2995	false	Chen, Yi-Rong and Tseng, Ching-Yu and Liou, Yi-Syuan and Wu, Tsung-Han and Hsu, Winston H.	given family Yi-Rong Chen given family Ching-Yu Tseng given family Yi-Syuan Liou given family Tsung-Han Wu given family Winston H. Hsu	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/chen23d/chen23d.pdf