Discover @ducha-aiki Open Source projects

Dmytro Mishkin (@ducha-aiki)

ducha-aiki

Stars
2,655
Global Rank 10,866 (Top 0.4 %)
Followers 613
Following 6
Registered almost 11 years ago
Most used languages

Jupyter Notebook
57.4 %

Python
21.3 %

C++
12.8 %

C
4.3 %

Roff 2.1 %

Shell
2.1 %
Location 🇨🇿 Czechia
Country Total Rank 54
Country Ranking

Jupyter Notebook
1

Roff 14

C++
21

Python
25

C
74

Shell
301

caffenet-benchmark

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

Jupyter Notebook

affnet

Code and weights for local feature affine shape estimation paper "Repeatability Is Not Enough: Learning Discriminative Affine Regions via Discriminability"

pydegensac

Advanced RANSAC (DEGENSAC) with bells and whistles for H and F estimation

pytorch-sift

PyTorch implementation of SIFT descriptor

Jupyter Notebook

manifold-diffusion

Diffusion on manifolds for image retrieval

LSUVinit

Reference caffe implementation of LSUV initialization

pyransac

Fast and accurate python RANSAC with LO, LAF-check

mods

MODS (Matching On Demand with view Synthesis) is algorithm for wide-baseline matching.

ransac-tutorial-2020-data

Starter kit for the CVPR 2020 RANSAC tutorial benchmark

Jupyter Notebook

pymagsac

MAGSAC: marginalizing sample consensus, python version

LSUV-keras

Simple implementation of the LSUV initialization in keras

navigation-benchmark

Code for "Benchmarking Classic and Learned Navigation in Complex 3D Environments" paper

google-retrieval-challenge-2019-fastai-starter

fast.ai starter kit for Google Landmark Retrieval 2019 challenge

Jupyter Notebook

LSUV-pytorch

Simple implementation of the LSUV initialization in PyTorch

mods-light-zmq

MODS with external deep descriptors/detectors

whale-identification-2018

Solution to Whale Identification Challenge 2018

Jupyter Notebook

extract_patches

Function for local patch extraction from OpenCV keypoints with proper bluring

Jupyter Notebook

numpy-sift

Numpy implementation of SIFT descriptor

Jupyter Notebook

matching-strategies-comparison

Comparison of the matching strategies for local feature descriptor

Jupyter Notebook

kornia_moons

Conversions between kornia and other computer vision libraries formats

Jupyter Notebook

hesaff-pytorch

PyTorch implementation of Hessian-Affine local feature detector

hardnet-in-fastai2-and-kornia

Re-implementation of local descriptor HardNet training in fasta2+kornia

Jupyter Notebook

fast_atan2

Realization of the atan2 approximations faster than standard function.

imc2021-sample-kornia-submission

Tutorial on how to create submission to Image Matching Challenge 2021

Jupyter Notebook

wide-baseline-stereo-blog

Blog about wide baseline stereo and local features

Jupyter Notebook

cpp-extract-patches

C++ header-only lib for extracting local patches

Jupyter Notebook

extract-patches-old

Simple function for local patch extraction from OpenCV keypoints.

Jupyter Notebook

pixelstitch

Simple tool for labelling the correspondences

Jupyter Notebook

imc2023-kornia-starter-pack

Simple jupyter notebook for 3D reconstruction using kornia and pycolmap

Jupyter Notebook

brown_phototour_revisited

New testing protocol for learning local patch descriptors on Brown Phototour dataset

Jupyter Notebook

vs3-cnn-labs

Computer vision labs for Vision and Sports Summer School 2022

Jupyter Notebook

mpv-templates-backup

Jupyter Notebook

wxbs-descriptors-benchmark

W1BS local patch descriptors benchmark

keras-sift

Jupyter Notebook

local_feature_tutorial

Some examples of how one can use local features

Jupyter Notebook

imagewoofv2-fastv2-maxpoolblur

Jupyter Notebook

caffe-preprocessing-scripts

Creates caffe lmdb from bunch of dirs with images. Clean-up, check, resize included

wxbs-benchmark

Code for benchmarking image matchers on WxBS dataset/

Jupyter Notebook

creating-data-for-imc

Scripts for creating benchmark data for IMC 2021 competition

ucn-pytorch

Jupyter Notebook

wisv2019-competition

Helper scripts for participation in http://cvg.dsi.unifi.it/cvg/index.php?id=caip-2019-contest

Jupyter Notebook

zeromqransac

COVID19-confirmed-cases-plot

Simple jupyter notebook to plot from John Hopkins data

Jupyter Notebook

nbu-reports-convert

Combine nbu reports to singlcsv

brown-revisited

Brown patch matching benchmark revisited

Jupyter Notebook

lsuv

Python package for neural network initialization

sam1