Efficient Graphics Representation with Differentiable Indirection
Sayantan Datta, Carl Marshall, Zhao Dong, Zhengqin Li, Derek Nowrouzezahrai · 2023
We introduce differentiable indirection – a novel learned primitive that employs differentiable multi-scale lookup tables as an effective substitute for traditional compute and data operations across the graphics pipeline. We demonstrate its flexibility on a number of graphics tasks, i.e., geometric and image representation, texture mapping, shading, and radiance field representation. In all cases, differentiable indirection seamlessly integrates into existing architectures, trains rapidly, and yields both versatile and efficient results.