GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lu, Yan, Ma, Xinzhu, Yang, Lei, Zhang, Tianzhu, Liu, Yating, Chu, Qi, He, Tong, Li, Yonghui, Ouyang, Wanli
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910774595682304
author Lu, Yan
Ma, Xinzhu
Yang, Lei
Zhang, Tianzhu
Liu, Yating
Chu, Qi
He, Tong
Li, Yonghui
Ouyang, Wanli
author_facet Lu, Yan
Ma, Xinzhu
Yang, Lei
Zhang, Tianzhu
Liu, Yating
Chu, Qi
He, Tong
Li, Yonghui
Ouyang, Wanli
contents Geometry plays a significant role in monocular 3D object detection. It can be used to estimate object depth by using the perspective projection between object's physical size and 2D projection in the image plane, which can introduce mathematical priors into deep models. However, this projection process also introduces error amplification, where the error of the estimated height is amplified and reflected into the projected depth. It leads to unreliable depth inferences and also impairs training stability. To tackle this problem, we propose a novel Geometry Uncertainty Propagation Network (GUPNet++) by modeling geometry projection in a probabilistic manner. This ensures depth predictions are well-bounded and associated with a reasonable uncertainty. The significance of introducing such geometric uncertainty is two-fold: (1). It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning. (2). It can be derived to a highly reliable confidence to indicate the quality of the 3D detection result, enabling more reliable detection inference. Experiments show that the proposed approach not only obtains (state-of-the-art) SOTA performance in image-based monocular 3D detection but also demonstrates superiority in efficacy with a simplified framework.
format Preprint
id arxiv_https___arxiv_org_abs_2310_15624
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
Lu, Yan
Ma, Xinzhu
Yang, Lei
Zhang, Tianzhu
Liu, Yating
Chu, Qi
He, Tong
Li, Yonghui
Ouyang, Wanli
Computer Vision and Pattern Recognition
Machine Learning
Geometry plays a significant role in monocular 3D object detection. It can be used to estimate object depth by using the perspective projection between object's physical size and 2D projection in the image plane, which can introduce mathematical priors into deep models. However, this projection process also introduces error amplification, where the error of the estimated height is amplified and reflected into the projected depth. It leads to unreliable depth inferences and also impairs training stability. To tackle this problem, we propose a novel Geometry Uncertainty Propagation Network (GUPNet++) by modeling geometry projection in a probabilistic manner. This ensures depth predictions are well-bounded and associated with a reasonable uncertainty. The significance of introducing such geometric uncertainty is two-fold: (1). It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning. (2). It can be derived to a highly reliable confidence to indicate the quality of the 3D detection result, enabling more reliable detection inference. Experiments show that the proposed approach not only obtains (state-of-the-art) SOTA performance in image-based monocular 3D detection but also demonstrates superiority in efficacy with a simplified framework.
title GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2310.15624