Differentiable Polarized Path Tracing

2026-07-14

AI Summary

This work addresses the limitations of existing differentiable rendering methods, which rely solely on radiance intensity and neglect the geometric and material constraints provided by polarization information. Furthermore, polarization operators formulated in the Mueller–Stokes framework suffer from rank deficiency, leading to unstable gradient estimation. To overcome these challenges, we propose a differentiable path tracing method that supports polarized light transport and, for the first time, enables stable backpropagation through the full Mueller–Stokes rendering pipeline. By introducing path replay and local gradient caching mechanisms, our approach effectively mitigates numerical instabilities arising from operations such as linear polarizers and diffuse reflection. The method significantly improves the efficiency and robustness of material and illumination parameter optimization in physics-based inverse rendering with polarization, thereby extending the applicability of differentiable rendering to polarimetric vision tasks.

Abstract

Physically based differentiable rendering has proven to be a powerful tool for inverse rendering problems (e.g., 3D reconstruction, reflectance estimation, lighting estimation). However, most existing methods operate solely on radiometric intensity, discarding valuable polarization cues that constrain scene geometry and 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. 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 and results 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 path replay and local caching. This formulation enables efficient and stable optimization of material and lighting parameters in complex scenes, broadening the applicability of physically based inverse rendering. Project page: https://vcai.mpi-inf.mpg.de/projects/DPPT/

Problem

• differentiable rendering
• polarization
• inverse rendering
• Mueller-Stokes calculus
• numerical instability

Innovation

• Differentiable Rendering
• Polarized Light
• Path Tracing
• Mueller-Stokes Calculus
• Inverse Rendering