Giter Site home page Giter Site logo

JiaxueLi's Projects

aanap icon aanap

An implementation of AANAP in CVPR 2015 paper.

caffe icon caffe

Caffe: a fast open framework for deep learning.

cs231n-2017 icon cs231n-2017

Completed the CS231n 2017 spring assignments from Stanford university

deepmatch icon deepmatch

Metric/Embedding learning using (convolutional) neural network with application to keypoint matching, stereo matching, image retrival, etc

fucking-algorithm icon fucking-algorithm

手把手撕LeetCode题目,扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.

gms-feature-matcher icon gms-feature-matcher

C++ code for "GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence"

image-stitching icon image-stitching

Leveraging Line-point Consistence to Preserve Structures for Wide Parallax Image Stitching

image_mosaic_stitching icon image_mosaic_stitching

Implemented a pipeline for 2D image mosaic and stitching. Feature extraction & matching, Adaptive Non-Maximal Suppression (ANMS), geometric blur, RANSAC

leetcode icon leetcode

LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解,记录自己的leetcode解题之路。)

niswgsp icon niswgsp

C++ implementation of the ECCV 2016 paper, Natural Image Stitching with the Global Similarity Prior.

panorama icon panorama

some papers of panorama, I will add some codes in the follow up process

pfnet icon pfnet

Code Repo of 'Rethinking Planar Homography Estimation Using Perspective Fields'

readme icon readme

README文件语法解读,即Github Flavored Markdown语法介绍

sparsecodingproject icon sparsecodingproject

Today we have Instagram, Facebook, Tumblr, Snapchat as the most used social networking sites and apps. Most of these are image based social networks. Due to the advent of such sites the raw data available for image processing has increased substantially. Now we have millions of images that are readily available. A hard problem that has received considerable attention is the batch alignment problem of images. Here you take multiple batches of images and align them to a fixed canonical template. This problem becomes harder to solve when we consider the difference in illumination, partial occlusion (presence of sunglasses, hats etc.) between the images of the same object. We implemented Robust Alignment by Sparse and Low-Rank Decomposition and simplified this challenging optimization problem into a sequence of convex programs with guaranteed fast convergence by applying the most efficient sequence of image-based transformations to breakdown the image matrix as a cumulation of a sparse matrix of errors plus a low-rank matrix of retrieved alignments. We will verify the efficacy of the proposed algorithm with extensive experiments with datasets

tfmatch icon tfmatch

TensorFlow implementation of GeoDesc (ECCV'18), ContextDesc (CVPR'19) and ASLFeat (CVPR'20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.