Fitting Spherical Gaussians to Dynamic HDRI Sequences

TL;DR

This paper introduces a method to efficiently fit anisotropic spherical Gaussians to dynamic HDRI sequences, ensuring temporal consistency and compact representation of complex lighting data.

Contribution

It presents a novel optimization-based approach that incorporates a temporal consistency loss for fitting spherical Gaussians to HDRI sequences.

Findings

Achieves compact representation of HDRI sequences with few parameters.

Ensures temporal consistency across the entire HDRI sequence.

Optimizes directions, sharpness, and intensity simultaneously.

Abstract

We present a technique for fitting high dynamic range illumination (HDRI) sequences using anisotropic spherical Gaussians (ASGs) while preserving temporal consistency in the compressed HDRI maps. Our approach begins with an optimization network that iteratively minimizes a composite loss function, which includes both reconstruction and diffuse losses. This allows us to represent all-frequency signals with a small number of ASGs, optimizing their directions, sharpness, and intensity simultaneously for an individual HDRI. To extend this optimization into the temporal domain, we introduce a temporal consistency loss, ensuring a consistent approximation across the entire HDRI sequence.