-
Czech Technical University in Prague
- Prague, Czechia
- https://dmytro.ai
- @ducha_aiki
Highlights
- Pro
Stars
a programming library with geometric algorithms
[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
A Unified Framework for Surface Reconstruction
A collaboration friendly studio for NeRFs
Geometric Computer Vision Library for Spatial AI
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 proces…
Monocular Depth Estimation Toolbox based on MMSegmentation.
Process and export Jupyter Notebooks fast (Jupyter not required)
[ICCV 2019] Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters - PyTorch
TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)
Official source code for "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems". In NeurIPS 2021.
Code for the Image similarity challenge.
The official Syft worker for Web and Node, built in Javascript
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
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
Cross-Descriptor Visual Localization and Mapping
pySLAM is a visual SLAM pipeline in Python for monocular, stereo and RGBD cameras. It supports many modern local and global features, different loop-closing methods, a volumetric reconstruction pip…
Template-based implementation of RANSAC and its variants in C++
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
Neural-Guided RANSAC for Estimating Epipolar Geometry from Sparse Correspondences
🐦 Quickly annotate data from the comfort of your Jupyter notebook