csjunxu Goto Github PK

awesome-meta-learning

A curated list of Meta-Learning resources/papers.

awesome-semantic-segmentation

:metal: awesome-semantic-segmentation

awesome-zero-shot-learning

A curated list of papers, code and resources pertaining to zero shot learning

badvideo

Course project for cs510 Computation Photography

bag-of-local-features-models

Pretrained bag-of-local-features neural networks

basic-computer-science-1525

basicsr

Basic Super-Resolution codes for development. Includes ESRGAN, SFT-GAN for training and testing.

beautygan

transfer the makeup of one face to another non-makeup face by histogram matching

benchmark_eps

A Benchmark for Edge-Preserving Image Smoothing.

benchmark_results

visual tracker benchmark results

beyond-part-models

PCB of paper: Beyond Part Models: Person Retrieval with Refined Part Pooling, using Pytorch

blind_image_quality_toolbox

Collection of Blind Image Quality Metrics in Matlab

blog

Source code and other material for my blog posts.

bm3dtip2007_junxu_modified

books

The books I like to read

born_again_neuralnet

bovik_niqe_spl2013

breezyslam

Simple, efficient, open-source package for Simultaneous Localization and Mapping in Python, Matlab, Java, and C++

burst-cvpr-2019

Iterative Residual CNNs for Burst Photography Applications

burst-denoising

caffe-fast-rcnn

Caffe fork that supports Faster R-CNN, all written in C++ (in c++-faster-rcnn branch)

caffe2

Caffe2 is a lightweight, modular, and scalable deep learning framework.

caffenet-benchmark

Evaluation of the CNN design choices performance on ImageNet-2012.

camera-pipeline-dng-sdk

camera-pipeline-ui

ccnet

CCNet achieves the state-of-the-art performance on Cityscapes and ADE20K.

ccnoise

The source code of "A Holistic Approach to Cross-Channel Image Noise Modeling and its Application to Image Denoising, CVPR16"

ccnoise_code_cvpr2016

code

ccsc_code_iccv2017

This is the source code repository for the ICCV 2017 paper "Consensus Convolutional Sparse Coding".

cfnet

[CVPR'17] Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to high performance at fast speed..