A$^2$TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation

TL;DR

This paper introduces A$^2$TG, an adaptive anisotropic textured Gaussian representation that improves 3D scene rendering efficiency by allocating textures non-uniformly based on scene details, reducing memory use and enhancing quality.

Contribution

It proposes a novel adaptive anisotropic textured Gaussian model that dynamically allocates texture resolution and aspect ratio, improving efficiency and visual fidelity over fixed-texture methods.

Findings

Reduces memory consumption compared to fixed-texture approaches.

Achieves comparable or better rendering quality on benchmark datasets.

Demonstrates significant efficiency gains in 3D scene representation.

Abstract

Gaussian Splatting has emerged as a powerful representation for high-quality, real-time 3D scene rendering. While recent works extend Gaussians with learnable textures to enrich visual appearance, existing approaches allocate a fixed square texture per primitive, leading to inefficient memory usage and limited adaptability to scene variability. In this paper, we introduce adaptive anisotropic textured Gaussians (A$^2$TG), a novel representation that generalizes textured Gaussians by equipping each primitive with an anisotropic texture. Our method employs a gradient-guided adaptive rule to jointly determine texture resolution and aspect ratio, enabling non-uniform, detail-aware allocation that aligns with the anisotropic nature of Gaussian splats. This design significantly improves texture efficiency, reducing memory consumption while enhancing image quality. Experiments on multiple benchmark datasets demonstrate that A TG consistently outperforms fixed-texture Gaussian Splatting methods, achieving comparable rendering fidelity with substantially lower memory requirements.