NeISF: Neural Incident Stokes Field for Geometry and Material Estimation

TL;DR

NeISF introduces a multi-view inverse rendering framework that leverages polarization cues and a differentiable polarimetric renderer to improve geometry and material estimation, especially in complex inter-reflection scenarios.

Contribution

The paper presents Neural Incident Stokes Fields (NeISF), a novel approach that incorporates polarization cues to effectively model multi-bounced light in inverse rendering.

Findings

Outperforms existing methods in synthetic scenarios

Effective in real-world inter-reflection cases

Accurately estimates scene geometry and materials

Abstract

Multi-view inverse rendering is the problem of estimating the scene parameters such as shapes, materials, or illuminations from a sequence of images captured under different viewpoints. Many approaches, however, assume single light bounce and thus fail to recover challenging scenarios like inter-reflections. On the other hand, simply extending those methods to consider multi-bounced light requires more assumptions to alleviate the ambiguity. To address this problem, we propose Neural Incident Stokes Fields (NeISF), a multi-view inverse rendering framework that reduces ambiguities using polarization cues. The primary motivation for using polarization cues is that it is the accumulation of multi-bounced light, providing rich information about geometry and material. Based on this knowledge, the proposed incident Stokes field efficiently models the accumulated polarization effect with the aid of an original physically-based differentiable polarimetric renderer. Lastly, experimental results show that our method outperforms the existing works in synthetic and real scenarios.