Anton Sergeyevich Kaplanyan has had an amazing career spanning all aspects of graphics technology. From a PhD in light transport to creating graphic technologies for Pixar and innovating VR visuals at Oculus, read how his amazing career journey has led Anton to a new position at Intel as VP of Graphics Research—and why he believes that Intel is poised to be at the forefront of a new era of graphics technology.
Falling in Love with Graphics
In 2002 I wrote my first path tracer running on an Intel® Celeron® processor. It was an indelible thrill for me to write a program and see a nice visual feedback on my efforts.
These early coding efforts led me to game development in 2004, inspired by the real-time visuals in games. I liked that by using math, I could develop better visuals for gamers around the world. After working on one of the first games to use deferred shading and DirectX 10, I saw a Game Developers Conference talk about CryEngine. This excited me enough to move from Russia to Germany to help work on CryEngine, one of the most beautiful game engines of its time. I enjoyed the power and scope of graphics research opportunities. Almost every colleague was a luminary who invented a new top-notch graphics technique. Thanks to the mentorship and encouragement of my manager and the R&D team, CryEngine 3 ended up being the first game engine delivering a working solution for fully dynamic real-time indirect lighting, which was also later adopted in multiple AAA games and game engines.
Down the Rabbit Hole–Light Transport Simulation and Research at Nvidia
I realized that the next qualitative visual breakthrough would likely come from the physically accurate simulation of light transport. Wanting to research this further, I switched back to academia and worked to look deeper into physically based light transport simulation. This ended up being my PhD topic. After finishing my PhD publications, I decided to try to develop one of the technologies. This was my first startup experience, which turned out to be a pleasant and exciting ride. We successfully integrated our technology into Pixar’s RenderMan engine and into their movies.
My career journey led me to working on the (back then) next-generation RTX hardware design for real-time ray tracing. I worked with some of the top graphics geniuses in the world on one of the most advanced new graphics hardware of the decade. In spite of the huge time difference between Finland and the U.S. West Coast, every interaction with the team significantly influenced not just my technical but also cultural research attitude.
After the hardware was done, my Nvidia Research colleagues and I realized that the hardware performance would not suffice for real-time visuals, so we started developing a completely new direction of real-time image reconstruction methods for ray tracing that ended up in games and Nvidia middleware.
Immersive Media and Gaze Contingent Rendering
Meanwhile, I had also started experimenting with VR headsets, and was astonished by how easily VR can trick the human visual system. This excitement about neural and perceptual graphics got me interested in the evolving media of VR and AR headsets and the graphics research problems therein. I joined Oculus Research (now Facebook Reality Labs Research) to help establish the new research lab and evolve graphics for this new medium. This was an unforgettable journey into so many different fields at the bleeding edge of physics, electronics, and human perception. With many recent publications, I was thrilled by our research team’s advancements in multiple subfields of modern graphics.
Have I mentioned that I am very excited about graphics research?
A Glimpse into the Future of Graphics
I think we are at the edge of a new era in graphics—an era where visual computing will become more distributed, more heterogeneous, more power-efficient, more accessible, and more intelligent. I see a strong trend to higher quality and quantity of visuals that is demanded by high-quality content creation and sharing, immersive remote communication, photorealistic games and movies, and high-resolution head-mounted displays, as well as photoreal simulation for more intelligent autonomous robots and vehicles.
I also think we have powerful new tools to meet these demands. Recent advances in neural graphics, ray tracing, cloud computing, perceptual and differentiable rendering, materials and lighting, appearance modeling, as well as in commoditized content creation require a transformation of the current graphics platform. This gives us an opportunity to not only completely reinvent how we co-design graphics hardware and software with these technologies in the driver’s seat, but also to look at a larger picture of a potentially novel graphics ecosystem that can include heterogenous distributed systems and multi-level compute for movie-quality visuals on a wide range of consumer devices. I believe these new demands and technologies make graphics one of the most exciting fields to be in.
The Future of Graphics at Intel
The key enabler to immersive graphics and the “Tony Stark” future is heavily reliant on intelligent computing. Computing that is instantly available at the cloud and the edge, and at network and scalable performance across displays, devices, and form factors. Intel is uniquely positioned at the frontier of new hardware technologies and silicon design and has all the technology building blocks in compute architecture, memory, packaging, and interconnect for advanced hardware architectures. Intel also has a long history in its integrated GPUs, and more recently has put some serious investment in the discrete GPU market. The combination of these two core businesses makes Intel a powerful new player in visual computing. I believe the new differentiating technologies in graphics and machine learning is the missing cherry on the cake that will allow Intel’s products to become gamers’ and practitioners’ favorite choice!
Looking for a career making world changing innovative technologies? Join us.