Pinned Repositories
agent_joggler
aggent_joggler is a warehouse simulator that implements multi-agent path planning with online task assignments.
anker
Anker is a telegram bot to add cards to Anki flash card.
Network-Simplex
A Python implementation of the Network Simplex algorithm applied to the shortest path problem.
OctoPrint-Telegram
Plugin for octoprint to send status messages and receive commands via Telegram messenger.
pointnet
Yet another pytorch implementation of "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation"
seminars
szobov.github.io
Personal blog
szobov's Repositories
szobov/agent_joggler
aggent_joggler is a warehouse simulator that implements multi-agent path planning with online task assignments.
szobov/OctoPrint-Telegram
Plugin for octoprint to send status messages and receive commands via Telegram messenger.
szobov/anker
Anker is a telegram bot to add cards to Anki flash card.
szobov/Network-Simplex
A Python implementation of the Network Simplex algorithm applied to the shortest path problem.
szobov/Robotics-Berlin.github.io
webpage
szobov/pointnet
Yet another pytorch implementation of "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation"
szobov/seminars
szobov/szobov.github.io
Personal blog
szobov/blenderpy
Blender as a python module with easy-install
szobov/blinder
Arduino scetch for my motorized roller blinds
szobov/bottle
bottle.py is a fast and simple micro-framework for python web-applications.
szobov/cgal
The public CGAL repository, see the README below
szobov/cpython
The Python programming language
szobov/cv
szobov/emacs-libvterm
Emacs libvterm integration
szobov/filterust
I'll implement here some filters after reading "Kalman and Bayesian Filters in Python" by R. Labbe but in rust
szobov/gatery
Gatery, a library for circuit design.
szobov/libigl
Simple C++ geometry processing library.
szobov/mavros
MAVLink to ROS gateway with proxy for Ground Control Station
szobov/Meshtastic-device
Device code for the Meshtastic ski/hike/fly/customizable open GPS radio
szobov/pgmq
A lightweight message queue. Like AWS SQS and RSMQ but on Postgres.
szobov/pip-tools
A set of tools to keep your pinned Python dependencies fresh.
szobov/pygbag-archives
archived prebuilts
szobov/pytest-parallel
A pytest plugin for parallel and concurrent testing
szobov/pytransform3d
3D transformations for Python.
szobov/pyvis
Python package for creating and visualizing interactive network graphs.
szobov/signoz
SigNoz is an open-source observability platform native to OpenTelemetry with logs, traces and metrics in a single application. An open-source alternative to DataDog, NewRelic, etc. 🔥 🖥. 👉 Open source Application Performance Monitoring (APM) & Observability tool
szobov/spdlog
Fast C++ logging library.
szobov/trigger-circleci-pipeline-action
Trigger a CircleCI pipeline from any GitHub Actions event.
szobov/VCMeshConv
Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.