wilsonax's Stars
Zdp1999/Multi-Scale-Exposure-Fusion-via-Adaptive-Well-Exposedness-and-3-D-Gradient
zhenglab/UnderwaterImageRestoration
Underwater Image Restoration.
earthat/Multi-Exposed-Image-Fusion-using-Deep-Learning
Fuse the multiple images with different exposure
zekunchen/Contour-Detection
zhaozunjin/RetinexDIP
The pytorch implementation of RetinexDIP, a unified zero-reference deep framework for low-light enhancement.
eddieyhlin/PnPRetinex
meilinxiaoxue/ptom_c
matlab pfile decrypt to mfile
hosseinhayati128/-Image-Contrast-and-Color-Enhancement-using-Adaptive-Gamma-Correction-and-Histogram-Equalization
arsenyinfo/EnlightenGAN-inference
ONNX Inference library for EnlightenGAN
Li-Chongyi/Zero-DCE_extension
KarelZhang/RUAS
[CVPR 2021] This is the official code for the paper "Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement"
VITA-Group/EnlightenGAN
[IEEE TIP] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
pratikgirigoswami/Exemplar-Based-Image-Inpainting
• Image inpainting is the process of seamlessly filling in holes of arbitrary topology in an image to preserve its overall continuity. It is an ancient art of fixing accidental damage and recreating lost information. • Object removal or modification in the original images can be carried out through image inpainting methods. • In this project, various algorithms of Partial Derivative Equation based and Exemplar-based families have been studied and implemented. Results using Total Variation (TV) and Curvature Driven Diffusion (CDD) methods show that CDD produces a better visual quality of results. However, it fails to restore texture information. • To solve this problem, Exemplar-based algorithms are studied and implemented. Traditionally, the data term present in this algorithm is based on the strength of the isophote found using the gradient. The problem with the gradient operator is studied, and a better contour preserving data term is proposed. The proposed data term uses the strength of structure line found using Infinite size Symmetric Exponential Filter (ISEF). This filter helps overcome the drawback of which overcomes the drawback of insensibility to noise and precision of edge localization present in traditional data term. • Results are compared by quantitative analysis using PSNR, SSIM, and FSIM. Subjective analysis is done using Mean Opinion Score. It is proved that the proposed method produces better visual results compared to few other existing exemplar-based methods. • Methods/Keywords: Exemplar-based Image Inpainting, PDE-based Image Inpainting, ISEF Filter, Priority Computation, Isophote, Curvature Driven Diffusion • Software/Tools/Programming Language Used: MATLAB, C
zhangprofessor/fast-Non-local-Means-and-Asymptotic-Non-local-Means
Non-Local means denoising (NLM) algorithm is a milestone algorithm in the field of image processing. The proposal of NLM has opened up the non-local method which has a deep influence. This paper performed a revisit for NLM from two aspects as follows: 1. To alleviate the high computational complexity problem of NLM, a fast algorithm was constructed, which was based on cross-correlation and fast Fourier transform; 2. NLM always blur structures and textures during the noise removal, especially in the case of strong noise. To solve this problem, an Asymptotic Non-Local Means image denoising algorithm is put forward, which uses the property of noise variance to control the filtering parameters. Numerical experiments illustrate that the fast algorithm is 27 times faster than classical implementation with standard parameter configuration, and the ANLM uniformly outperforms classical NLM, in terms of both PSNR and visual effects.
koujan/Robotics-Course-project
Haze can cause poor visibility and loss of contrast in images and videos. In this article, we study the dehazing problem which can improve visibility and thus help in many computer vision applications. An extensive comparison of state of the art single image dehazing methods is done. One simple contrast enhancement method is used for dehazing. Structure- texture decomposition has been used in conjunction with this enhancement method to improve its performance in presence of synthetic noise. Methods which use a haze formation model and attempt at solving an ill-posed problem using computer vision priors are also investigated. The two priors studied are dark channel prior and the non-local prior. Both qualitative and quantitative comparisons for atmospheric and underwater images on all three methods provide a conclusive idea of which dehazing method performs better. All this knowledge has been extended to video dehazing. A video dehazing method which uses the spatial and temporal information in a video is studied in depth. An improved version of video dehazing is proposed in this article, which uses the spatial-temporal information fusion framework but does not suffer from some of its limitations. The new video dehazing method is shown to produce better results on test videos
banzheshitou/Scale-aware-Guided-and-Structure-Preserved-Texture-Filter
Scale-aware Guided and Structure Preserved Texture Filter
yqx7150/matlabcode_SGTD
SGTD: Structure gradient and texture decorrelating regularization for image decomposition
gkh178/an-improved-NLM-image-denoising-algorithm-based-on-edge-detection
Aiming at the removal of gaussian noise, we systematically analyze the shortage of non-local means image denonising algorithm (NLM), finding it is easy to lose structure information when dealing with the image containing complex edges and textures by NLM algorithm. In order to solve this problem, a non-local means image denoising based on edge detection is proposed in this thesis. The innovation of the proposed algorithm is mainly manifested in the following : (1) An improved Sobel operator with eight directions is proposed to extract a more accurate edge image; (2) To make the neighborhoods with similar structure obtain more weight, not only the Euclidean distance but also the edge image are considered when the similarity of neighborhoods is measured. Many experiments demonstrate that in both subjective and objective evaluation principles the performance of the improved algorithm has a good effect, and the visual effect of the denoised image is good.
tonghelen/LR3M-Method
Image Enhancing
pvnieo/Low-light-Image-Enhancement
Python implementation of two low-light image enhancement techniques via illumination map estimation
csjunxu/STAR-TIP2020
Matlab code for STAR: A Structure and Texture Aware Retinex Model, TIP 2020.
andrew-pengjj/Enhanced-3DTV
The code of enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing
HaoNingWu/ETV
This is a collection of two MATLAB demos of Algorithms 1 (image denoising) and 2 (image reconstruction) in the paper "Enhanced total variation minimization for stable image reconstruction" by Congpei An, Hao-Ning Wu, and Xiaoming Yuan.
cqucs/Frequency_based
lilong10/quaternion
Signal Processing by Quaternion Arithmetic
Huang-chao-yan/pQSTV
This is the code of paper ``Total Variation Based Pure Quaternion Dictionary Learning Method for Color Image Denoising'', Tingting Wu, Chaoyan Huang, Zhengmeng Jin, Zhigang Jia, and Michael K. Ng
Huang-chao-yan/QWNNM
This is the code of ''Chaoyan Huang, Zhi Li, Yubing Liu, Tingting Wu, Tieyong Zeng, Quaternion-based weighted nuclear norm minimization for color image restoration, Pattern Recognition,Volume 128, 2022, 108665.
chaofengc/Awesome-Image-Quality-Assessment
A comprehensive collection of IQA papers
kenjihiranabe/The-Art-of-Linear-Algebra
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
StefanoMesselodi/Super
Fast implementation of a Retinex like algorithm