Computing Light Transport Gradients using the Adjoint Method
This work addresses a specific computational bottleneck in rendering for graphics researchers, offering a novel theoretical approach that could ease gradient-based optimizations.
The paper tackles the problem of computing gradients in light transport by deriving a new equation from continuous adjoint theory, showing that gradient computation is equivalent to computing the importance field, which simplifies implementation in existing path tracers.
This paper proposes a new equation from continuous adjoint theory to compute the gradient of quantities governed by the Transport Theory of light. Unlike discrete gradients ala autograd, which work at the code level, we first formulate the continuous theory and then discretize it. The key insight of this paper is that computing gradients in Transport Theory is akin to computing the importance, a quantity adjoint to radiance that satisfies an adjoint equation. Importance tells us where to look for light that matters. This is one of the key insights of this paper. In fact, this mathematical journey started from a whimsical thought that these adjoints might be related. Computing gradients is therefore no more complicated than computing the importance field. This insight and the following paper hopefully will shed some light on this complicated problem and ease the implementations of gradient computations in existing path tracers.