SOURCE-LINKED INTELLIGENCE

Compact Neural Appearance Models for Efficient Gaussian Splatting

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Explicit primitive-based radiance fields such as 3D Gaussian Splatting typically model view-dependent appearance using low-order spherical harmonics (SH). Although efficient to evaluate, SH coefficients dominate per-primitive storage and memory traffic, while their band-limited basis restricts angular detail. We present a thorough, end-to-end comparison of SH and recent spherical appearance models and introduce an implicit alternative that decodes compact per-primitive latent codes using a tiny shared MLP. We integrate all models into the same optimized pipeline, fusing their forward and backw

Read original source ↗ Open in workspace

recordType

paper

region

Global