Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation

TL;DR

This paper introduces Implicit Gaussian Splatting, a hybrid 3D representation combining explicit point clouds with implicit features, achieving high-quality rendering with significantly reduced storage requirements.

Contribution

The paper proposes a novel implicit-explicit hybrid model with a multi-level tri-plane architecture and a progressive training scheme for efficient, high-fidelity 3D rendering.

Findings

High-quality rendering with only a few MBs of data

Effective balancing of storage efficiency and rendering fidelity

Competitive results with state-of-the-art methods

Abstract

Recent advancements in photo-realistic novel view synthesis have been significantly driven by Gaussian Splatting (3DGS). Nevertheless, the explicit nature of 3DGS data entails considerable storage requirements, highlighting a pressing need for more efficient data representations. To address this, we present Implicit Gaussian Splatting (IGS), an innovative hybrid model that integrates explicit point clouds with implicit feature embeddings through a multi-level tri-plane architecture. This architecture features 2D feature grids at various resolutions across different levels, facilitating continuous spatial domain representation and enhancing spatial correlations among Gaussian primitives. Building upon this foundation, we introduce a level-based progressive training scheme, which incorporates explicit spatial regularization. This method capitalizes on spatial correlations to enhance both the rendering quality and the compactness of the IGS representation. Furthermore, we propose a novel compression pipeline tailored for both point clouds and 2D feature grids, considering the entropy variations across different levels. Extensive experimental evaluations demonstrate that our algorithm can deliver high-quality rendering using only a few MBs, effectively balancing storage efficiency and rendering fidelity, and yielding results that are competitive with the state-of-the-art.