Zobrazeno 1 - 10
of 75
pro vyhledávání: '"Yin, Xiaoting"'
Estimating Neural Radiance Fields (NeRFs) from images captured under optimal conditions has been extensively explored in the vision community. However, robotic applications often face challenges such as motion blur, insufficient illumination, and hig
Externí odkaz:
http://arxiv.org/abs/2410.16995
Autor:
Shi, Hao, Wang, Song, Zhang, Jiaming, Yin, Xiaoting, Wang, Zhongdao, Wang, Guangming, Zhu, Jianke, Yang, Kailun, Wang, Kaiwei
Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard processing, struggle with simultaneous geometric and semantic estimation,
Externí odkaz:
http://arxiv.org/abs/2403.08504
3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as human-computer interacti
Externí odkaz:
http://arxiv.org/abs/2401.16700
Human pose estimation is a fundamental and appealing task in computer vision. Although traditional cameras are commonly applied, their reliability decreases in scenarios under high dynamic range or heavy motion blur, where event cameras offer a robus
Externí odkaz:
http://arxiv.org/abs/2311.04591
Autor:
Du, Yongkun, Chen, Zhineng, Jia, Caiyan, Yin, Xiaoting, Li, Chenxia, Du, Yuning, Jiang, Yu-Gang
Scene text recognition (STR) methods have struggled to attain high accuracy and fast inference speed. Autoregressive (AR)-based models implement the recognition in a character-by-character manner, showing superiority in accuracy but with slow inferen
Externí odkaz:
http://arxiv.org/abs/2307.12270
Autor:
Ye, Yaozu, Shi, Hao, Yang, Kailun, Wang, Ze, Yin, Xiaoting, Lin, Yining, Liu, Mao, Wang, Yaonan, Wang, Kaiwei
Optical flow estimation is a fundamental task in the field of autonomous driving. Event cameras are capable of responding to log-brightness changes in microseconds. Its characteristic of producing responses only to the changing region is particularly
Externí odkaz:
http://arxiv.org/abs/2307.05033
Vision sensors are widely applied in vehicles, robots, and roadside infrastructure. However, due to limitations in hardware cost and system size, camera Field-of-View (FoV) is often restricted and may not provide sufficient coverage. Nevertheless, fr
Externí odkaz:
http://arxiv.org/abs/2211.11293
Autor:
Li, Chenxia, Liu, Weiwei, Guo, Ruoyu, Yin, Xiaoting, Jiang, Kaitao, Du, Yongkun, Du, Yuning, Zhu, Lingfeng, Lai, Baohua, Hu, Xiaoguang, Yu, Dianhai, Ma, Yanjun
Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and accuracy, we pr
Externí odkaz:
http://arxiv.org/abs/2206.03001
Autor:
Du, Yongkun, Chen, Zhineng, Jia, Caiyan, Yin, Xiaoting, Zheng, Tianlun, Li, Chenxia, Du, Yuning, Jiang, Yu-Gang
Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In this study,
Externí odkaz:
http://arxiv.org/abs/2205.00159
Autor:
Shi, Hao, Zhou, Yifan, Yang, Kailun, Yin, Xiaoting, Wang, Ze, Ye, Yaozu, Yin, Zhe, Meng, Shi, Li, Peng, Wang, Kaiwei
Optical flow estimation is a basic task in self-driving and robotics systems, which enables to temporally interpret traffic scenes. Autonomous vehicles clearly benefit from the ultra-wide Field of View (FoV) offered by 360{\deg} panoramic sensors. Ho
Externí odkaz:
http://arxiv.org/abs/2202.13388