favcode Goto Github PK

followers: 1.0 following: 0.0 repos: 168.0 gists: 0.0

Type: User

favcode's Projects

-ui

A UI library by WeChat official design team, includes the most useful widgets/modules in mobile web applications.

-vue-quasar-company-profile-website

Kudos - Company profile website made using Vue.js and Quasar Framework

0--illumination-pca-ii

Generate illumination-invariant grayscale image using PCA

0-deep-learning-for-document-dewarping

An application of high resolution GANs to dewarp images of perturbed documents

0-deform-image-morphing

Automating Image Morphing using Structural Similarity on a Halfway Domain （Siggraph 2014）

0-deform-morphlib

A simplfied library for Image Morphing algorithm

0-deform-torch-warp

Fully automatic optical flow based image morphing implemented in Torch

0-deformation-aware-unpaired-image-translation

This repo contains code for CVPR2020 paper: Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

0-dewarping-document-image-by-displacement-flow-estimation

Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network

0-illumination--lime

Implementation of the paper, "LIME: Low-Light Image Enhancement via Illumination Map Estimation", which is for my graduation thesis.

0-illumination-monte_carlo_ray_tracer

A program with an implemented Monte Carlo Ray Tracer algorithm for global illumination of a virtual 3D scene.

0-illumination-surface-estimation-and-image-relighting

Illumination registration, surface estimation, and physically-based image relighting

0-image_based_relighting_framework

Framework that implements three image-based relighting algorithms.

0-multi-illuminant-based-color-constancy

Combining bottom-up and top-down visual mechanisms for color constancy under varying illumination. This repository contains the datasets and codes published for color constancy under varying illmunations. -----------COPYRIGHT NOTICE STARTS WITH THIS LINE------------ Copyright (c) 2019 All rights reserved. This doucuments are a rough version for summarizing the results and codes in publication [1], which is available only for research purpose. We preserve the rights to further correct and update the data. This dataset contains three datasets for color constancy under varying illuminations, which are used in publication [1]. real-world dataset with multi-illuminant: the real-world dataset contains 37 images captured under vairous non-uniform light sources. synthetic dataset with multi-illuminant: the dataset with the synthetic multiple illuminants contains 100 images. MCC-BU+TD: This dataset contains results of multiple MCC algorithms on several real-world images taken from the web, which could be easily used and compared in any research publications. More information please refer to readme.txt in each folder. If you use this dataset for the evaluation of your approach and producing the results, please cite our work as follows: [1] S. Gao, Y. Ren, M. Zhang and Y. Li, "Combining bottom-up and top-down visual mechanisms for color constancy under varying illumination," in IEEE Transactions on Image Processing. doi: 10.1109/TIP.2019.2908783 [2] X.-S. Zhang, S.-B. Gao, R.-X. Li, X.-Y. Du, C.-Y. Li, and Y.-J. Li, “A retinal mechanism inspired color constancy model,” IEEE Transactions on Image Processing, vol. 25, no. 3, pp. 1219–1232, 2016. [3] K.-F. Yang, S.-B. Gao, Y.-J. Li, and Y. Li, “Efficient illuminant estimation for color constancy using grey pixels,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 2254–2263. [4] Gao, S. B., Yang, K. F., Li, C. Y., & Li, Y. J. (2015). Color constancy using double-opponency. IEEE transactions on pattern analysis and machine intelligence, 37(10), 1973-1985. Any questions and comments are welcome to [email protected]