Synthesizing high-fidelity head avatars is a central problem for computer vision and graphics. While head avatar synthesis algorithms have advanced rapidly, the best ones still face great obstacles in real-world scenarios.

While 3D Gaussians efficiently approximate an object's surface, they fail to capture the volumetric properties of subsurface scattering. We propose a framework for optimizing an object's shape together with the radiance transfer field given multi-view OLA T (one light at a time) data.

V olume rendering in neural radiance fields is inherently time-consuming due to the large number of MLP calls on the points sampled per ray. Previous works would address this issue by introducing new neural networks or data structures. In this work, we propose GL-NeRF, a new perspective of computing volume rendering with the Gauss-Laguerre quadrature.

Additionally, we introduce a Bézier-boundary gradient approximation strategy within our framework to keep the "differentiability"

Despite its potential, 3DGS encounters challenges such as needle-like artifacts, suboptimal geometries, and inaccurate normals caused by the Gaussians converging into anisotropic shapes with one dominant variance.

In this paper we present a novel method for efficient and effective 3D surface reconstruction in open scenes.