Differentiable Polarized Path Tracing

Physically based differentiable rendering has proven to be a powerful tool for inverse rendering problems (e.g., 3D reconstruction). However, most existing methods operate solely on radiometric intensity, discarding valuable polarization cues that constrain material properties. While forward simulation of polarized light is well-defined via Mueller–Stokes calculus, extending reverse-mode differentiation to this domain presents significant challenges. Specifically, the rank-deficient nature of common polarimetric operators—such as linear polarizers and diffuse reflections—violates the invertibility assumptions of standard gradient estimators like Path Replay Backpropagation (PRB), resulting in numerical instability. We address this by proposing a robust, polarization-aware differentiable path tracing method. Our approach estimates unbiased gradients through a combination of recursive recomputation and local caching. This formulation enables the efficient and stable optimization of material and lighting parameters in complex scenes.