Zobrazeno 1 - 10
of 220
pro vyhledávání: '"Chen, Shaoyu"'
Text presented in augmented reality provides in-situ, real-time information for users. However, this content can be challenging to apprehend quickly when engaging in cognitively demanding AR tasks, especially when it is presented on a head-mounted di
Externí odkaz:
http://arxiv.org/abs/2402.18797
Autor:
Chen, Shaoyu, Jiang, Bo, Gao, Hao, Liao, Bencheng, Xu, Qing, Zhang, Qian, Huang, Chang, Liu, Wenyu, Wang, Xinggang
Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. In this work, to cope with the uncertainty problem, we propose VADv2, an end-
Externí odkaz:
http://arxiv.org/abs/2402.13243
Autor:
Castelo, Sonia, Rulff, Joao, McGowan, Erin, Steers, Bea, Wu, Guande, Chen, Shaoyu, Roman, Iran, Lopez, Roque, Brewer, Ethan, Zhao, Chen, Qian, Jing, Cho, Kyunghyun, He, He, Sun, Qi, Vo, Huy, Bello, Juan, Krone, Michael, Silva, Claudio
The concept of augmented reality (AR) assistants has captured the human imagination for decades, becoming a staple of modern science fiction. To pursue this goal, it is necessary to develop artificial intelligence (AI)-based methods that simultaneous
Externí odkaz:
http://arxiv.org/abs/2308.06246
Autor:
Liao, Bencheng, Chen, Shaoyu, Zhang, Yunchi, Jiang, Bo, Zhang, Qian, Liu, Wenyu, Huang, Chang, Wang, Xinggang
High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system. In this paper, we present \textbf{Map} \text
Externí odkaz:
http://arxiv.org/abs/2308.05736
Autor:
Chen, Shaoyu, Zhang, Yunchi, Liao, Bencheng, Xie, Jiafeng, Cheng, Tianheng, Sui, Wei, Zhang, Qian, Huang, Chang, Liu, Wenyu, Wang, Xinggang
High-definition (HD) map serves as the essential infrastructure of autonomous driving. In this work, we build up a systematic vectorized map annotation framework (termed VMA) for efficiently generating HD map of large-scale driving scene. We design a
Externí odkaz:
http://arxiv.org/abs/2304.09807
Autor:
Chen, Shaoyu, Cheng, Tianheng, Fang, Jiemin, Zhang, Qian, Li, Yuan, Liu, Wenyu, Wang, Xinggang
Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors. To accurately detect small objects with limited
Externí odkaz:
http://arxiv.org/abs/2304.03428
Autor:
Jiang, Bo, Chen, Shaoyu, Xu, Qing, Liao, Bencheng, Chen, Jiajie, Zhou, Helong, Zhang, Qian, Liu, Wenyu, Huang, Chang, Wang, Xinggang
Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representation (e.g., agent occupancy and semantic map) to perform planning, whic
Externí odkaz:
http://arxiv.org/abs/2303.12077
Autor:
Liao, Bencheng, Chen, Shaoyu, Jiang, Bo, Cheng, Tianheng, Zhang, Qian, Liu, Wenyu, Huang, Chang, Wang, Xinggang
Online lane graph construction is a promising but challenging task in autonomous driving. Previous methods usually model the lane graph at the pixel or piece level, and recover the lane graph by pixel-wise or piece-wise connection, which breaks down
Externí odkaz:
http://arxiv.org/abs/2303.08815
Autor:
Jiang, Bo, Chen, Shaoyu, Wang, Xinggang, Liao, Bencheng, Cheng, Tianheng, Chen, Jiajie, Zhou, Helong, Zhang, Qian, Liu, Wenyu, Huang, Chang
Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving. In this work, we propose PIP, the first end-to-end Transformer-based framework which jointly and interactively p
Externí odkaz:
http://arxiv.org/abs/2212.02181
Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding boxes. Whi
Externí odkaz:
http://arxiv.org/abs/2210.05174