Deep Richardson–Lucy Deconvolution for Low-Light Image Deblurring

Images taken under the low-light condition often contain blur and saturated pixels at the same time. Deblurring images with saturated pixels is quite challenging. Because of the limited dynamic range, the saturated pixels are usually clipped in the imaging process and thus cannot be modeled by the l...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision 2024-02, Vol.132 (2), p.428-445
Main Authors: Chen, Liang, Zhang, Jiawei, Li, Zhenhua, Wei, Yunxuan, Fang, Faming, Ren, Jimmy, Pan, Jinshan
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Blurring
Computer Imaging
Computer Science
Image Processing and Computer Vision
Image quality
Methods
Neural networks
Pattern Recognition
Pattern Recognition and Graphics
Pixels
Posterior sections
Special Issue on Physics-Based Vision meets Deep Learning
Vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Images taken under the low-light condition often contain blur and saturated pixels at the same time. Deblurring images with saturated pixels is quite challenging. Because of the limited dynamic range, the saturated pixels are usually clipped in the imaging process and thus cannot be modeled by the linear blur model. Previous methods use manually designed smooth functions to approximate the clipping procedure. Their deblurring processes often require empirically defined parameters, which may not be the optimal choices for different images. In this paper, we develop a data-driven approach to model the saturated pixels by a learned latent map. Based on the new model, the non-blind deblurring task can be formulated into a maximum a posterior problem, which can be effectively solved by iteratively computing the latent map and the latent image. Specifically, the latent map is computed by learning from a map estimation network, and the latent image estimation process is implemented by a Richardson–Lucy (RL)-based updating scheme. To estimate high-quality deblurred images without amplified artifacts, we develop a prior estimation network to obtain prior information, which is further integrated into the RL scheme. Experimental results demonstrate that the proposed method performs favorably against state-of-the-art algorithms both quantitatively and qualitatively on synthetic and real-world images.
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-023-01877-9