Zobrazeno 1 - 10
of 4 151
pro vyhledávání: '"Liu, Qiong A."'
Along with the advancements in artificial intelligence technologies, image-to-point-cloud registration (I2P) techniques have made significant strides. Nevertheless, the dimensional differences in the features of points cloud (three-dimension) and ima
Externí odkaz:
http://arxiv.org/abs/2410.00360
Optical imaging systems are generally limited by the depth of field because of the nature of the optics. Therefore, extending depth of field (EDoF) is a fundamental task for meeting the requirements of emerging visual applications. To solve this task
Externí odkaz:
http://arxiv.org/abs/2409.19220
4D occupancy forecasting is one of the important techniques for autonomous driving, which can avoid potential risk in the complex traffic scenes. Scene flow is a crucial element to describe 4D occupancy map tendency. However, an accurate scene flow i
Externí odkaz:
http://arxiv.org/abs/2409.15841
Autor:
Xie, Huidong, Guo, Liang, Velo, Alexandre, Liu, Zhao, Liu, Qiong, Guo, Xueqi, Zhou, Bo, Chen, Xiongchao, Tsai, Yu-Jung, Miao, Tianshun, Xia, Menghua, Liu, Yi-Hwa, Armstrong, Ian S., Wang, Ge, Carson, Richard E., Sinusas, Albert J., Liu, Chi
Rb-82 is a radioactive isotope widely used for cardiac PET imaging. Despite numerous benefits of 82-Rb, there are several factors that limits its image quality and quantitative accuracy. First, the short half-life of 82-Rb results in noisy dynamic fr
Externí odkaz:
http://arxiv.org/abs/2409.11543
A residual deep reinforcement learning (RDRL) approach is proposed by integrating DRL with model-based optimization for inverter-based volt-var control in active distribution networks when the accurate power flow model is unknown. RDRL learns a resid
Externí odkaz:
http://arxiv.org/abs/2408.06790
Inverter-based volt-var control is studied in this paper. One key issue in DRL-based approaches is the limited measurement deployment in active distribution networks, which leads to problems of a partially observable state and unknown reward. To addr
Externí odkaz:
http://arxiv.org/abs/2408.06776
Autor:
Chen, Tianqi, Hou, Jun, Zhou, Yinchi, Xie, Huidong, Chen, Xiongchao, Liu, Qiong, Guo, Xueqi, Xia, Menghua, Duncan, James S., Liu, Chi, Zhou, Bo
Positron Emission Tomography (PET) is an important clinical imaging tool but inevitably introduces radiation hazards to patients and healthcare providers. Reducing the tracer injection dose and eliminating the CT acquisition for attenuation correctio
Externí odkaz:
http://arxiv.org/abs/2406.08374
Autor:
Xie, Huidong, Gan, Weijie, Zhou, Bo, Chen, Ming-Kai, Kulon, Michal, Boustani, Annemarie, Spencer, Benjamin A., Bayerlein, Reimund, Ji, Wei, Chen, Xiongchao, Liu, Qiong, Guo, Xueqi, Xia, Menghua, Zhou, Yinchi, Liu, Hui, Guo, Liang, An, Hongyu, Kamilov, Ulugbek S., Wang, Hanzhong, Li, Biao, Rominger, Axel, Shi, Kuangyu, Wang, Ge, Badawi, Ramsey D., Liu, Chi
Reducing scan times, radiation dose, and enhancing image quality, especially for lower-performance scanners, are critical in low-count/low-dose PET imaging. Deep learning (DL) techniques have been investigated for PET image denoising. However, existi
Externí odkaz:
http://arxiv.org/abs/2405.12996
Autor:
Xia, Menghua, Xie, Huidong, Liu, Qiong, Zhou, Bo, Wang, Hanzhong, Li, Biao, Rominger, Axel, Shi, Kuangyu, Fakhri, Georges EI, Liu, Chi
Deep learning-based positron emission tomography (PET) image denoising offers the potential to reduce radiation exposure and scanning time by transforming low-count images into high-count equivalents. However, existing methods typically blur crucial
Externí odkaz:
http://arxiv.org/abs/2404.17994
Enabling Large Language Models (LLMs) to interact with 3D environments is challenging. Existing approaches extract point clouds either from ground truth (GT) geometry or 3D scenes reconstructed by auxiliary models. Text-image aligned 2D features from
Externí odkaz:
http://arxiv.org/abs/2404.13044