Zobrazeno 1 - 10
of 152
pro vyhledávání: '"Zha, Zhiyuan"'
The compressive sensing (CS) scheme exploits much fewer measurements than suggested by the Nyquist-Shannon sampling theorem to accurately reconstruct images, which has attracted considerable attention in the computational imaging community. While cla
Externí odkaz:
http://arxiv.org/abs/2203.09656
Publikováno v:
In Signal Processing September 2024 222
Publikováno v:
In Information Fusion August 2024 108
Publikováno v:
In Knowledge-Based Systems 19 July 2024 296
State-of-the-art image denoisers exploit various types of deep neural networks via deterministic training. Alternatively, very recent works utilize deep reinforcement learning for restoring images with diverse or unknown corruptions. Though deep rein
Externí odkaz:
http://arxiv.org/abs/2107.05318
Publikováno v:
In Expert Systems With Applications 15 June 2024 244
Publikováno v:
In Journal of Membrane Science March 2024 695
Publikováno v:
In Carbon Capture Science & Technology March 2024 10
Constructing effective image priors is critical to solving ill-posed inverse problems in image processing and imaging. Recent works proposed to exploit image non-local similarity for inverse problems by grouping similar patches and demonstrated state
Externí odkaz:
http://arxiv.org/abs/2006.13714
Publikováno v:
2020 International Conference on Image Processing
Recent works that utilized deep models have achieved superior results in various image restoration applications. Such approach is typically supervised which requires a corpus of training images with distribution similar to the images to be recovered.
Externí odkaz:
http://arxiv.org/abs/2005.07902