ProbeSDF: Light Field Probes for Neural Surface Reconstruction

TL;DR

ProbeSDF introduces a minimal radiance parametrization for neural surface reconstruction that decouples angular and spatial contributions, enabling faster computation, real-time rendering, and improved performance across diverse datasets.

Contribution

The paper presents a physically-inspired, minimal radiance parametrization for SDF-based neural surface reconstruction that enhances speed and performance with fewer parameters and efficient implementation.

Findings

Achieves real-time rendering and faster training speeds.

Improves surface and image quality metrics (PSNR).

Consistently performs well across diverse datasets.

Abstract

SDF-based differential rendering frameworks have achieved state-of-the-art multiview 3D shape reconstruction. In this work, we re-examine this family of approaches by minimally reformulating its core appearance model in a way that simultaneously yields faster computation and increased performance. To this goal, we exhibit a physically-inspired minimal radiance parametrization decoupling angular and spatial contributions, by encoding them with a small number of features stored in two respective volumetric grids of different resolutions. Requiring as little as four parameters per voxel, and a tiny MLP call inside a single fully fused kernel, our approach allows to enhance performance with both surface and image (PSNR) metrics, while providing a significant training speedup and real-time rendering. We show this performance to be consistently achieved on real data over two widely different and popular application fields, generic object and human subject shape reconstruction, using four representative and challenging datasets.