Neural Radiosity
This work addresses rendering challenges in computer graphics for scenes with complex surfaces, offering a novel method that improves upon traditional radiosity techniques.
The paper tackles the problem of solving the rendering equation for scenes with non-diffuse surfaces by introducing Neural Radiosity, which uses neural networks to represent the full radiance distribution and optimize parameters to minimize residual norms, enabling efficient synthesis of arbitrary views and demonstrating effectiveness on various scenes.
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.