Real2sim
Drone video becomes a photorealistic 3D copy of the place, where drones can be trained.
- 597k Gaussians from 88 photos for $0.75 of cloud time
- PX4 flight simulator over the digital twin
- Automatically labelled data for training detectors
1+ year of commercial experience · open to projects
Python & AI engineer. I build production systems that work with real-world data: computer vision on phone video, LLM agents, 3D models generated from map data, and the automation that runs an online store. From prototype to deploy, on my own.
Below: 10 projects, what each one solves, how it works step by step and the numbers it delivered. The three main ones run live right on the page.
About
PythonFastAPIaiogramCelerypandas
PyTorchONNX RuntimeMediaPipeRTMPoseOpenCV
OpenAIGeminiClaudeChromaDB
trimeshosmnxOpen3DBlenderThree.js
TypeScriptReactNext.js
PostgreSQLRedisDockerGitHub Actions
01 · 3D and geodata
OpenStreetMap and elevation data turned into clean, printable geometry: 3D city models for sale, digital twins, point clouds for simulation.
The monadruk generator turns maps and terrain into a model for 3D printing. Here the same approach runs on the real Matterhorn: heights from open satellite data, 4 × 4 km, sliced into 0.2 mm layers. Scroll and it prints.
How it works →Real prints
Also in this area
Drone video becomes a photorealistic 3D copy of the place, where drones can be trained.
02 · Computer vision
Pose, 3D body and measurements from an ordinary phone video, with an honest error bar on every number.
One ordinary camera, one jump. On the left is what the system measures, on the right the original. Scroll to move through the clip; every number is read from the system's own run on this video.
Also in this area
A coach films an exercise on a phone. The system lifts the movement out of the video and a 3D skater repeats it, so the skating app can teach the exercise without showing the coach's footage or voice.
03 · Automation and AI
Telegram bots, job queues, marketplace feeds, LLM product copy and CRM integrations running for a real business.
At a clothing manufacturer, managers send a product video to a Telegram bot. Queues take it from there. Scroll to follow one upload.
How it works →Also in this area
An online shop inside Telegram, with no separate website.

Stock from a shop's warehouse program turns into product cards on its website, Rozetka and Facebook by itself.


A small window on top of the warehouse program that counts every scanned item during a stocktake.

From a library of books the system makes a narrated, illustrated video on its own.

A personal trainer for getting hired: voice mock interviews, a study course with an AI mentor, and a job feed that picks the vacancies worth the effort.



Working together
Marketplace feeds for Rozetka, Prom, Epicentr and Horoshop, stock sync from UkrSklad, product descriptions written by AI and checked before publishing.
Bots with queues that never block the chat, WebApp shops with a cart, delivery and CRM integrations.
Pose and motion from ordinary phone video, measured and honest about uncertainty; video generated end to end.
Examples:jumpsightLodykAI Video Studio
Map and elevation data turned into printable models and digital twins; geometry that survives real data.
I start from your real files, chats and edge cases, not from an ideal spec.
A working slice within days, so we argue about results instead of slides.
Every system gets a check it has to pass, and the cases it cannot handle are documented.
Deployment, CI, logs and alerts. I use AI coding agents for speed and keep tests and benchmarks as the judge.
About a year building the automation behind a manufacturer's online sales: Telegram bots, job queues, marketplace feeds, AI-written product copy, sales analytics and CI/CD.
Printable 3D models of real places, from map data to payment. Live.
jumpsight, Lodyk and Real2sim: pose estimation, motion solving and synthetic data.
Stock sync and marketplace feeds, a stocktake counter for a warehouse, a Telegram shop.
Full-stack projects in React, TypeScript and Node: shops, journals, kanban boards.
Contact
Earth imagery: NASA GIBS (VIIRS on NOAA-20, true colour, previous day), NASA Visible Earth (Blue Marble by month, Black Marble). ISS position: wheretheiss.at. Relief: Solar System Scope, CC BY 4.0, via the three.js examples.