Diffusion Posterior Illumination for Ambiguity-aware Inverse Rendering

TL;DR

This paper introduces a novel inverse rendering method that leverages diffusion models to better handle ambiguities in scene illumination and material estimation, producing realistic and diverse environment maps.

Contribution

It integrates a diffusion probabilistic model with a differentiable path tracer to improve ambiguity-aware inverse rendering, a novel approach in the field.

Findings

Produces highly realistic environment maps

Excels in recovering materials from images

Generates diverse illumination samples

Abstract

Inverse rendering, the process of inferring scene properties from images, is a challenging inverse problem. The task is ill-posed, as many different scene configurations can give rise to the same image. Most existing solutions incorporate priors into the inverse-rendering pipeline to encourage plausible solutions, but they do not consider the inherent ambiguities and the multi-modal distribution of possible decompositions. In this work, we propose a novel scheme that integrates a denoising diffusion probabilistic model pre-trained on natural illumination maps into an optimization framework involving a differentiable path tracer. The proposed method allows sampling from combinations of illumination and spatially-varying surface materials that are, both, natural and explain the image observations. We further conduct an extensive comparative study of different priors on illumination used in previous work on inverse rendering. Our method excels in recovering materials and producing highly realistic and diverse environment map samples that faithfully explain the illumination of the input images.