MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Models

TL;DR

MixLight introduces a hybrid model combining Spherical Harmonics and Spherical Gaussian models, along with a novel sparse light source module, to improve scene illumination estimation for mixed reality applications, outperforming existing methods.

Contribution

The paper proposes a joint SH and SG model with a new sparsemax module for better illumination representation and generalization in scene lighting estimation.

Findings

Surpasses state-of-the-art methods on multiple metrics.

Demonstrates better generalization on Web Dataset.

Effectively captures both low-frequency and high-frequency lighting components.

Abstract

Accurately estimating scene lighting is critical for applications such as mixed reality. Existing works estimate illumination by generating illumination maps or regressing illumination parameters. However, the method of generating illumination maps has poor generalization performance and parametric models such as Spherical Harmonic (SH) and Spherical Gaussian (SG) fall short in capturing high-frequency or low-frequency components. This paper presents MixLight, a joint model that utilizes the complementary characteristics of SH and SG to achieve a more complete illumination representation, which uses SH and SG to capture low-frequency ambient and high-frequency light sources respectively. In addition, a special spherical light source sparsemax (SLSparsemax) module that refers to the position and brightness relationship between spherical light sources is designed to improve their sparsity, which is significant but omitted by prior works. Extensive experiments demonstrate that MixLight surpasses state-of-the-art (SOTA) methods on multiple metrics. In addition, experiments on Web Dataset also show that MixLight as a parametric method has better generalization performance than non-parametric methods.