Efficient Graphics Representation with Differentiable Indirection

09/12/2023
by   Sayantan Datta, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset