MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Models
This addresses the challenge of incomplete illumination representation in mixed reality applications, offering an incremental improvement over existing parametric models.
The paper tackles the problem of accurately estimating scene lighting for mixed reality by proposing MixLight, a joint model that combines Spherical Harmonics and Spherical Gaussian models to capture both low-frequency ambient and high-frequency light sources, achieving state-of-the-art performance on multiple metrics and showing better generalization than non-parametric methods.
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.