Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Fang, Liangji"'
3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding. Owing to its low cost and high efficiency, multi-view 3D object detection has demonstrated promising application prospects. However, a
Externí odkaz:
http://arxiv.org/abs/2211.09386
Point clouds and RGB images are two general perceptional sources in autonomous driving. The former can provide accurate localization of objects, and the latter is denser and richer in semantic information. Recently, AutoAlign presents a learnable par
Externí odkaz:
http://arxiv.org/abs/2207.10316
Autor:
Li, Zhenyu, Chen, Zehui, Li, Ang, Fang, Liangji, Jiang, Qinhong, Liu, Xianming, Jiang, Junjun
Monocular 3D object detection (Mono3D) has achieved tremendous improvements with emerging large-scale autonomous driving datasets and the rapid development of deep learning techniques. However, caused by severe domain gaps (e.g., the field of view (F
Externí odkaz:
http://arxiv.org/abs/2205.11664
Autor:
Li, Zhenyu, Chen, Zehui, Li, Ang, Fang, Liangji, Jiang, Qinhong, Liu, Xianming, Jiang, Junjun
Monocular 3D object detection (Mono3D) has achieved unprecedented success with the advent of deep learning techniques and emerging large-scale autonomous driving datasets. However, drastic performance degradation remains an unwell-studied challenge f
Externí odkaz:
http://arxiv.org/abs/2204.11590
3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding. Due to its low cost and high efficiency, multi-view 3D object detection has demonstrated promising application prospects. However, acc
Externí odkaz:
http://arxiv.org/abs/2204.11582
Autor:
Chen, Zehui, Li, Zhenyu, Zhang, Shiquan, Fang, Liangji, Jiang, Qinghong, Zhao, Feng, Zhou, Bolei, Zhao, Hang
Object detection through either RGB images or the LiDAR point clouds has been extensively explored in autonomous driving. However, it remains challenging to make these two data sources complementary and beneficial to each other. In this paper, we pro
Externí odkaz:
http://arxiv.org/abs/2201.06493
Autor:
Li, Zhenyu, Chen, Zehui, Li, Ang, Fang, Liangji, Jiang, Qinhong, Liu, Xianming, Jiang, Junjun, Zhou, Bolei, Zhao, Hang
Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional space, su
Externí odkaz:
http://arxiv.org/abs/2112.04680
Predicting multiple plausible future trajectories of the nearby vehicles is crucial for the safety of autonomous driving. Recent motion prediction approaches attempt to achieve such multimodal motion prediction by implicitly regularizing the feature
Externí odkaz:
http://arxiv.org/abs/2103.11624
Making accurate motion prediction of the surrounding traffic agents such as pedestrians, vehicles, and cyclists is crucial for autonomous driving. Recent data-driven motion prediction methods have attempted to learn to directly regress the exact futu
Externí odkaz:
http://arxiv.org/abs/2004.12255
Recently, leveraging on the development of end-to-end convolutional neural networks (CNNs), deep stereo matching networks have achieved remarkable performance far exceeding traditional approaches. However, state-of-the-art stereo frameworks still hav
Externí odkaz:
http://arxiv.org/abs/1903.01700