Dmytro Mishkin

py_mtasklite. A missing piece of the Python multitask (both threads and processes) API: An extension that supports stateful worker pools & size-aware iterators.

kindly-web-search-mcp-server. Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.

RoMaV2. Python

geogram. a programming library with geometric algorithms

banned-in-ca. Python

tandem. [CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

hlb-CIFAR10. Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

sdfstudio. A Unified Framework for Surface Reconstruction

nerfstudio. A collaboration friendly studio for NeRFs

ida_lib. Image augmentation library

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

ARKitScenes. This repo accompanies the research paper, ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data and contains the data, scripts to visualize and process assets, and training code described in our paper.

Monocular-Depth-Estimation-Toolbox. Monocular Depth Estimation Toolbox based on MMSegmentation.

nbprocess-old. Process and export Jupyter Notebooks fast (Jupyter not required)

Key.Net-Pytorch. [ICCV 2019] Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters - PyTorch

tf-metal-experiments. TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)

locs. Official source code for "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems". In NeurIPS 2021.

isc2021. Code for the Image similarity challenge.

syft.js. The official Syft worker for Web and Node, built in Javascript

freelabel. FreeLabel: A Publicly Available Annotation Tool based on Freehand Traces - Code used for our manuscript presented at Winter Conference on Applications of Computer Vision (WACV), 2019

rebiber. A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

cross-descriptor-vis-loc-map. Cross-Descriptor Visual Localization and Mapping

asmk. Python implementation of ASMK

mlad-benchmark-baselines. Python

pyslam. pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

RansacLib. Template-based implementation of RANSAC and its variants in C++

BlendedMVS. BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

sfm_benchmark_release. Python

msc-data-science-ucu. MSc in Data Science at UCU

r2d2. Python

pytorch-metric-learning. The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

ngransac. Neural-Guided RANSAC for Estimating Epipolar Geometry from Sparse Correspondences

pigeon. 🐦 Quickly annotate data from the comfort of your Jupyter notebook

ICCV2019-Horde. Code repository for our paper entilted "Metric Learning with HORDE: High-Order Regularizer for Deep Embeddings" accepted at ICCV 2019.

FM-Bench. An Evaluation of Feature Matchers for Fundamental Matrix Estimation (BMVC 2019)

repeats. Repeats

python_cpp_example. An example of a hybrid python/C++ package with unit tests

diffusion. Efficient Diffusion for Image Retrieval

d2-net. D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

contextdesc. Implementation of CVPR'19 paper (oral) - ContextDesc: Local Descriptor Augmentation with Cross-Modality Context

overboard. Pure Python dashboard for monitoring deep learning experiments (like TensorBoard for PyTorch/JAX/etc, without a browser)

hyperbolic-image-embeddings. Supplementary code for the paper "Hyperbolic Image Embeddings".

arxiv-latex-cleaner. arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Saliency-Sampler. The saliency-based is a distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task.

ncnet. PyTorch code for Neighbourhood Consensus Networks

fenchel-young-losses. Probabilistic classification in PyTorch/TensorFlow/scikit-learn with Fenchel-Young losses

pretrained-models.pytorch. Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

mirror. Matchable Image Retrieval by Learning from Surface Reconstruction

pcam. The PatchCamelyon (PCam) deep learning classification benchmark.

neural_renderer. A PyTorch port of the Neural 3D Mesh Renderer

parallelHesaff. OpenMP implementation of the Hessian Affine detector with SIFT descriptor (original code: http://github.com/perdoch/hesaff)

fastai. The fastai deep learning library

taskonomy. Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]

cifar10_docker. Jupyter Notebook

relational-rnn-pytorch. An implementation of DeepMind's Relational Recurrent Neural Networks (NeurIPS 2018) in PyTorch.

imageio. Python library for reading and writing image data

Augmented-Deep-Reinforcement-Learning-for-3D-environments. C++

vlb-deteval. Comprehensive detector evaluation of local feature detectors

SuperPointPretrainedNetwork. PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

minos. MINOS: Multimodal Indoor Simulator

ORB-SLAM2-GPU2016-final. C++

diffusion-retrieval. Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

dfp. Direct Future Prediction Agent for MINOS

mlcrate. A python module of handy tools and functions, mainly for ML and Kaggle

revisitop. Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

umap. Uniform Manifold Approximation and Projection

equation_solver. Python

ANMS-Codes. Efficient adaptive non-maximal suppression algorithms for homogeneous spatial keypoint distribution

FastPhotoStyle. Style transfer, deep learning, feature transform

tfwss. Weakly Supervised Segmentation with Tensorflow. Implements instance segmentation as described in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).

pytorch-deform-conv. PyTorch implementation of Deformable Convolution

pysparnn. Approximate Nearest Neighbor Search for Sparse Data in Python!

PS-Dataset. PhotoSynth Dataset for improving local patch Descriptors

turicreate. Turi Create simplifies the development of custom machine learning models.

vise. (MIRROR of https://gitlab.com/vgg/vise) VGG Image Search Engine (VISE) is a standalone software for visual search of large image collections using image region as search query.

cnngeometric_pytorch. CNNGeometric PyTorch implementation

tps_stn_pytorch. PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)

RDS. edge detection

mkd. MATLAB implementation of the multiple-kernel local-patch descriptor (BMVC 2017 paper)

super-convergence. Files to create the figures in the paper "Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates"

Spread-out_Local_Feature_Descriptor. Code for Learning Spread-out Local Feature Descriptors

nuts-ml. Flow-based data pre-processing for deep learning

DeepCD. [ICCV17] DeepCD: Learning Deep Complementary Descriptors for Patch Representations

foolbox. A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

catboost. A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

cnnimageretrieval. CNN Image Retrieval in MatConvNet: Training and evaluating CNNs for Image Retrieval in MatConvNet

local-feature-evaluation. Comparative Evaluation of Hand-Crafted and Learned Local Features

quiver. Interactive convnet features visualization for Keras

Transform_Covariant_Detector. Matlab

FASText. Efficient Unconstrained Scene Text Detector

shake-shake. 2.86% and 15.85% on CIFAR-10 and CIFAR-100

textfool. Plausible looking adversarial examples for text classification

kde. Kernelized Local Descriptors

L2-Net. Code and mode for CVPR 2017 paper "L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space"

visdom. A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy https://visdom.dev

STN.keras. Implementation of spatial transformer networks (STNs) in keras 2 with tensorflow as backend.

hesaff. Hessian Affine detector with SIFT descriptor, CMP implementation

LIFT. Code release for the ECCV 2016 paper

keras-multiprocess-image-data-generator. Accelerating Deep Learning with Multiprocess Image Augmentation in Keras

luna16. LUNA16 Lung Nodule Analysis - NWI-IMC037 Final Project

DeepLearningImplementations. Implementation of recent Deep Learning papers

hyperboard. A web-based dashboard for Deep Learning

awesome-computer-vision. A curated list of awesome computer vision resources

transferability-advdnn-pub. Public repo for transferability ICLR 2017 paper

pix2pix. Image-to-image translation with conditional adversarial nets

fb-caffe-exts. Some handy utility libraries and tools for the Caffe deep learning framework.

Deep-Learning-Papers-Reading-Roadmap. Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

nips2016. Learning What and Where to Draw

hpatches-benchmark. Python & Matlab code for local feature descriptor evaluation with the HPatches dataset.

MetalDetector. GoogLeNet on iOS demo

BaiduImageCrawler. A multithreaded tool for downloading search results of Baidu image search.

layer-norm. Code and models from the paper "Layer Normalization"

imagenet-validation.torch. Fast and easy testing of imagenet models

terrapattern. Enabling journalists, citizen scientists, humanitarian workers and others to detect “patterns of interest” in satellite imagery.

torch-lsuv. Torch implementation of LSUV weight init from http://arxiv.org/abs/1511.06422

transformer_network. Spatial Transformer network

Learned-Activation-Functions-Source. For the reproduction of research by Agostinelli et al. Learning Activation Functions to Improve Deep Neural Networks. http://arxiv.org/abs/1412.6830

google_inception_v3_for_caffe. Google Inception (deepdream) v3 for Caffe

crow. Cross-dimensional weighting for aggregated deep convolutional features.

CaffeOnSpark. Distributed deep learning on Hadoop and Spark clusters.

F9Lander. Simple 2d simulation of Falcon 9 rocket landing on an ocean platform (Python)

tensorflow. An Open Source Machine Learning Framework for Everyone

imsearch-tools. Python utilities for automated download of images from various web sources

rspringer. :no_entry: ARCHIVED :no_entry:

caffe. Caffe: a fast open framework for deep learning.