Inverse Global Illumination using a Neural Radiometric Prior

05/03/2023
by   Saeed Hadadan, et al.
0

Inverse rendering methods that account for global illumination are becoming more popular, but current methods require evaluating and automatically differentiating millions of path integrals by tracing multiple light bounces, which remains expensive and prone to noise. Instead, this paper proposes a radiometric prior as a simple alternative to building complete path integrals in a traditional differentiable path tracer, while still correctly accounting for global illumination. Inspired by the Neural Radiosity technique, we use a neural network as a radiance function, and we introduce a prior consisting of the norm of the residual of the rendering equation in the inverse rendering loss. We train our radiance network and optimize scene parameters simultaneously using a loss consisting of both a photometric term between renderings and the multi-view input images, and our radiometric prior (the residual term). This residual term enforces a physical constraint on the optimization that ensures that the radiance field accounts for global illumination. We compare our method to a vanilla differentiable path tracer, and more advanced techniques such as Path Replay Backpropagation. Despite the simplicity of our approach, we can recover scene parameters with comparable and in some cases better quality, at considerably lower computation times.

READ FULL TEXT

page 1

page 7

page 8

page 9

page 12

page 14

research
01/31/2022

Differentiable Neural Radiosity

We introduce Differentiable Neural Radiosity, a novel method of represen...
research
04/14/2022

Modeling Indirect Illumination for Inverse Rendering

Recent advances in implicit neural representations and differentiable re...
research
05/26/2023

Joint Optimization of Triangle Mesh, Material, and Light from Neural Fields with Neural Radiance Cache

Traditional inverse rendering techniques are based on textured meshes, w...
research
05/26/2021

Neural Radiosity

We introduce Neural Radiosity, an algorithm to solve the rendering equat...
research
11/30/2022

Plateau-free Differentiable Path Tracing

Current differentiable renderers provide light transport gradients with ...
research
04/01/2021

Efficient and Differentiable Shadow Computation for Inverse Problems

Differentiable rendering has received increasing interest for image-base...
research
09/30/2021

Accelerating Inverse Rendering By Using a GPU and Reuse of Light Paths

Inverse rendering seeks to estimate scene characteristics from a set of ...

Please sign up or login with your details

Forgot password? Click here to reset