Proceedings ArticleDOI
Image Deblurring via Extreme Channels Prior
Yanyang Yan,Wenqi Ren,Yuanfang Guo,Rui Wang,Xiaochun Cao +4 more
- pp 6978-6986
TLDR
This work observes that the bright pixels in the clear images are not likely to be bright after the blur process, and proposes a technique fordeblurring such images which elevates the performance of existing motion deblurring algorithms and takes advantage of both Bright and Dark Channel Prior.Abstract:
Camera motion introduces motion blur, affecting many computer vision tasks. Dark Channel Prior (DCP) helps the blind deblurring on scenes including natural, face, text, and low-illumination images. However, it has limitations and is less likely to support the kernel estimation while bright pixels dominate the input image. We observe that the bright pixels in the clear images are not likely to be bright after the blur process. Based on this observation, we first illustrate this phenomenon mathematically and define it as the Bright Channel Prior (BCP). Then, we propose a technique for deblurring such images which elevates the performance of existing motion deblurring algorithms. The proposed method takes advantage of both Bright and Dark Channel Prior. This joint prior is named as extreme channels prior and is crucial for achieving efficient restorations by leveraging both the bright and dark information. Extensive experimental results demonstrate that the proposed method is more robust and performs favorably against the state-of-the-art image deblurring methods on both synthesized and natural images.read more
Citations
More filters
Proceedings ArticleDOI
Learning to Super-Resolve Blurry Face and Text Images
Xiangyu Xu,Xiangyu Xu,Xiangyu Xu,Deqing Sun,Deqing Sun,Jinshan Pan,Yu-Jin Zhang,Hanspeter Pfister,Ming-Hsuan Yang +8 more
TL;DR: This work presents an algorithm to directly restore a clear highresolution image from a blurry low-resolution input and introduces novel training losses that help recover fine details.
Proceedings ArticleDOI
Deep Semantic Face Deblurring
TL;DR: Zhang et al. as mentioned in this paper proposed to incorporate global semantic priors as input and impose local structure losses to regularize the output within a multi-scale deep CNN to restore sharp images with more facial details.
Proceedings ArticleDOI
Neural Blind Deconvolution Using Deep Priors
TL;DR: Experimental results show that the proposed SelfDeblur can achieve notable quantitative gains as well as more visually plausible deblurring results in comparison to state-of-the-art blind deconvolution methods on benchmark datasets and real-world blurry images.
Proceedings ArticleDOI
Blind Image Deblurring With Local Maximum Gradient Prior
TL;DR: A blind deblurring method based on Local Maximum Gradient (LMG) prior, inspired by the simple and intuitive observation that the maximum value of a local patch gradient will diminish after the blur process, which is proved to be true both mathematically and empirically.
Journal ArticleDOI
Deep Video Dehazing With Semantic Segmentation
TL;DR: This paper develops a deep learning solution for video dehazing, where a CNN is trained end-to-end to learn how to accumulate information across frames for transmission estimation, and proposes to incorporate global semantic priors as input to regularize the transmission maps.
References
More filters
Journal ArticleDOI
$L_0$ -Regularized Intensity and Gradient Prior for Deblurring Text Images and Beyond
TL;DR: The proposed image prior is based on distinctive properties of text images, with which an efficient optimization algorithm is developed to generate reliable intermediate results for kernel estimation and an effective method to remove artifacts for better deblurred results is presented.
Journal ArticleDOI
Framelet-Based Blind Motion Deblurring From a Single Image
TL;DR: This paper focuses on how to recover a motion-blurred image due to camera shake and proposes a regularization-based approach to remove motion blurring from the image by regularizing the sparsity of both the original image and the motion- Blur kernel under tight wavelet frame systems.
Journal ArticleDOI
Image Deblurring via Enhanced Low-Rank Prior
TL;DR: An enhanced prior for image deblurring is introduced by combining the low rank prior of similar patches from both the blurry image and its gradient map, and a weighted nuclear norm minimization method is employed to further enhance the effectiveness of low-rank prior.
Proceedings ArticleDOI
Handling Noise in Single Image Deblurring Using Directional Filters
TL;DR: This work proposes a new method for handling noise in blind image deconvolution based on new theoretical and practical insights, and observes that applying a directional low-pass filter to the input image greatly reduces the noise level, while preserving the blur information in the orthogonal direction to the filter.
Proceedings ArticleDOI
Deblurring Low-Light Images with Light Streaks
TL;DR: This work introduces a non-linear blur model that explicitly models light streaks and their underlying light sources, and poses them as constraints for estimating the blur kernel in an optimization framework, and automatically detects useful light streaks in the input image.