Technical Papers

Date/Time: 04 – 13 December 2020
All presentations are available in the virtual platform on-demand.

Lecturer(s):
Samuli Laine, NVIDIA, Finland
Janne Hellsten, NVIDIA, Finland
Tero Karras, NVIDIA, Finland
Yeongho Seol, NVIDIA, South Korea
Jaakko Lehtinen, NVIDIA, Aalto University, Finland
Timo Aila, NVIDIA, Finland

Bio:

Description: We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines. Our design supports all crucial operations in a modern graphics pipeline: rasterizing large numbers of triangles, attribute interpolation, filtered texture lookups, as well as user-programmable shading and geometry processing, all in high resolutions. Our modular primitives allow custom, high-performance graphics pipelines to be built directly within automatic differentiation frameworks such as PyTorch or TensorFlow. As a motivating application, we formulate facial performance capture as an inverse rendering problem and show that it can be solved efficiently using our tools. Our results indicate that this simple and straightforward approach achieves excellent geometric correspondence between rendered results and reference imagery.