We introduce Neural Radiosity, an algorithm to solve the rendering equation by minimizing the norm of its residual similar as in traditional radiosity techniques. Traditional basis functions used in radiosity techniques, such as piecewise polynomials or meshless basis functions are typically limited to representing isotropic scattering from diffuse surfaces. Instead, we propose to leverage neural networks to represent the full four-dimensional radiance distribution, directly optimizing network parameters to minimize the norm of the residual. Our approach decouples solving the rendering equation from rendering (perspective) images similar as in traditional radiosity techniques, and allows us to efficiently synthesize arbitrary views of a scene. In addition, we propose a network architecture using geometric learnable features that improves convergence of our solver compared to previous techniques. Our approach leads to an algorithm that is simple to implement, and we demonstrate its effectiveness on a variety of scenes with non-diffuse surfaces.
@article{Hadadan2021NeRad,
doi = {10.1145/3478513.3480569},
url = {https://doi.org/10.1145%2F3478513.3480569},
year = 2021,
month = {dec},
publisher = {Association for Computing Machinery ({ACM})},
volume = {40},
number = {6},
pages = {1--11},
author = {Saeed Hadadan and Shuhong Chen and Matthias Zwicker},
title = {Neural radiosity},
journal = {{ACM} Transactions on Graphics}
}