activity
20172021
most citedA Physics-based Noise Formation Model for Extreme Low-light Raw Denoising

15 citations · 23 across the 4 of their papers we have counts for

collaborators

7 papers

eess.IV2021

Snapshot Hyperspectral Imaging Based on Weighted High-order Singular Value Regularization

Niankai Cheng, Hua Huang, Lei Zhang +1

Snapshot hyperspectral imaging can capture the 3D hyperspectral image (HSI) with a single 2D measurement and has attracted increasing attention recently. Recovering the underlying…

cs.CV2020

TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems

Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang +3

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 den…

eess.IV202015 cited

A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising

Kaixuan Wei, Ying Fu, Jiaolong Yang +1

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 proble…

cs.CV2020

3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising

Kaixuan Wei, Ying Fu, Hua Huang

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 --…

eess.IV2020

Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems

Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang +3

Plug-and-play (PnP) is a non-convex framework that combines ADMM or other proximal algorithms with advanced denoiser priors. Recently, PnP has achieved great empirical success, esp…

cs.CV20194 cited

Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements

Kaixuan Wei, Jiaolong Yang, Ying Fu +2

Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems. Although state-of-the-art methods can o…