Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Wei, Kaixuan"'
The realm of classical phase retrieval concerns itself with the arduous task of recovering a signal from its Fourier magnitude measurements, which are fraught with inherent ambiguities. A single-exposure intensity measurement is commonly deemed insuf
Externí odkaz:
http://arxiv.org/abs/2311.10950
Autor:
Wei, Kaixuan, Li, Xiao, Froech, Johannes, Chakravarthula, Praneeth, Whitehead, James, Tseng, Ethan, Majumdar, Arka, Heide, Felix
The explosive growth of computation and energy cost of artificial intelligence has spurred strong interests in new computing modalities as potential alternatives to conventional electronic processors. Photonic processors that execute operations using
Externí odkaz:
http://arxiv.org/abs/2308.03407
Existing instance segmentation techniques are primarily tailored for high-visibility inputs, but their performance significantly deteriorates in extremely low-light environments. In this work, we take a deep look at instance segmentation in the dark
Externí odkaz:
http://arxiv.org/abs/2304.14298
Publikováno v:
Neurocomputing 481 (2022) 281-293
Deep-learning-based hyperspectral image (HSI) restoration methods have gained great popularity for their remarkable performance but often demand expensive network retraining whenever the specifics of task changes. In this paper, we propose to restore
Externí odkaz:
http://arxiv.org/abs/2209.08240
Autor:
Deng, Jia-Nan, Zhao, Honghao, Zheng, Hao, Zhuang, Yuan, Wei, Kaixuan, Yuan, Haozhong, Deng, Zhanhua, Gao, Yuanxian, Zhou, Xing, Yu, Tianteng, Hu, Huiting, Lu, Guiwu, Zhang, Xiao
Publikováno v:
In Fuel 1 January 2025 379
Enhancing the visibility in extreme low-light environments is a challenging task. Under nearly lightless condition, existing image denoising methods could easily break down due to significantly low SNR. In this paper, we systematically study the nois
Externí odkaz:
http://arxiv.org/abs/2108.02158
Compressive imaging aims to recover a latent image from under-sampled measurements, suffering from a serious ill-posed inverse problem. Recently, deep neural networks have been applied to this problem with superior results, owing to the learned advan
Externí odkaz:
http://arxiv.org/abs/2107.11007
Autor:
Wei, Kaixuan, Aviles-Rivero, Angelica, Liang, Jingwei, Fu, Ying, Huang, Hua, Schönlieb, Carola-Bibiane
Plug-and-Play (PnP) is a non-convex optimization framework that combines proximal algorithms, for example, the alternating direction method of multipliers (ADMM), with advanced denoising priors. Over the past few years, great empirical success has be
Externí odkaz:
http://arxiv.org/abs/2012.05703
Lacking rich and realistic data, learned single image denoising algorithms generalize poorly to real raw images that do not resemble the data used for training. Although the problem can be alleviated by the heteroscedastic Gaussian model for noise sy
Externí odkaz:
http://arxiv.org/abs/2003.12751
In this paper, we propose an alternating directional 3D quasi-recurrent neural network for hyperspectral image (HSI) denoising, which can effectively embed the domain knowledge -- structural spatio-spectral correlation and global correlation along sp
Externí odkaz:
http://arxiv.org/abs/2003.04547