Mikhail (Mike) Dereviannykh specializes in graphics and deep learning, focusing on direct and inverse rendering, both online and offline. He earned his BS in Software Engineering from HSE University in 2021, receiving scholarships for his success in programming tournaments. After starting a Master's in 2022, he fast-tracked to a PhD-student in 2023 at KIT’s Institute for Visualization and Data under Prof. Dr. C. Dachsbacher. His research covers differentiable rendering, neural networks for real-time rendering with tensor cores, and links between rendering and generative image models.
Previously, Mike founded WellDone Games and developed the mobile game Hungry Jump. He later joined Eagle Dynamics as a Rendering Engineer for DCS World, a AAA flight simulator. By 2021, he became a Senior Rendering R&D Engineer, leading the VFX Damaging System project and working on real-time AI global illumination and rendering optimizations.
email: devmishok@gmail.com
Neural Two-Level Monte Carlo Real-Time Rendering
Mikhail Dereviannykh, Dmitrii Klepikov, Johannes Hanika, Carsten Dachsbacher
Eurographics 2025
Arxiv Version | Video Demo: High Res and Low Res
Real-Time Path-Guiding Based on Parametric Mixture Model
Mikhail Derevyannykh
Eurographics 2022
Conference Version | Fast Forward | Video Presentation | Video Demo
DCS World VFX System - Senior Graphics Programmer
- Developed a real-time GI algorithm (0.1ms update) using neural networks and distributed computing
- Researched path-guiding for real-time rendering, presented at Eurographics 2022.
- Built and optimized graphics effects, PBR volumetrics, and a particle editor.
- Boosted engine performance with NSight, VTune, and C++/LUA optimizations.
Video Steam
Hungry Jump - CTO/Co-Founder of WellDone Games
- Led development, ensuring smooth shipping, QA, and game design integration.
- Delivered a polished game with 100 levels, 16 unique AI-driven insects, and 10+ custom UI screens.
- Built a scalable data system (Google Spreadsheets + Python) managing 1M+ logic cells.
- Engineered advanced insect flight physics using Markov Chain Random Walk.
- Optimized performance and animations with Cocos2d-x + GAFMedia.
Video Google Play