Mikhail Derevyannykh

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 2022 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 gaming 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

linkedin twitter bsky

Updates:
- Meshy Fellowship 2025 Outstanding Prize Recipient [New] [Link] - 20.02.25
- I started a PhD at KIT, IVD [Link] - 22.07.22
- Gave a talk about "Real-Time Neural Graphics" at Intel, GPU Research - 05.01.22

Neural Two-Level Monte Carlo Real-Time Rendering

Mikhail Dereviannykh, Dmitrii Klepikov, Johannes Hanika, Carsten Dachsbacher

Eurographics 2025

TLTR: We introduce Neural Incident Radiance Cache (NIRC) enabling efficient integration over a neural network domain instead of relying on costly path tracing. To ensure unbiased estimations and improved accuracy, we employ a Two-Level Monte Carlo approach, outperforming Neural Control Variates in training speed and representative power

Paper | Project Page

Real-Time Path-Guiding Based on Parametric Mixture Model

Mikhail Derevyannykh

Eurographics 2022

TLTR: The first lightweight screen-space path-guiding for real-time use, based on online learning of parametric mixture models. 4× FLIP metric reduction at 1 spp, runs in <1.5ms on RTX 2070 at 1080p, and improves path coherence by 5%, reducing bias and SVGF flickering

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