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.
Cite
@article{arxiv.2412.06511,
title = {Fitting Spherical Gaussians to Dynamic HDRI Sequences},
author = {Pascal Clausen and Li Ma and Mingming He and Ahmet Levent Tasel and Oliver Pilarski and Paul Debevec},
journal= {arXiv preprint arXiv:2412.06511},
year = {2024}
}
Comments
3 pages, 4 figures, SIGGRAPH Asia 2024 poster, https://www.eyelinestudios.com/research/hdri_sg_fit.html