Modular primitives for high-performance differentiable rendering

Samuli Laine*, Janne Hellsten, Tero Karras, Yeongho Seol, Jaakko Lehtinen, Timo Aila

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review


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.
Original languageEnglish
Article number194
Number of pages14
JournalACM Transactions on Graphics
Issue number6
Publication statusPublished - Dec 2020
MoE publication typeA1 Journal article-refereed

Fingerprint Dive into the research topics of 'Modular primitives for high-performance differentiable rendering'. Together they form a unique fingerprint.

Cite this