Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior

TL;DR

Fast-2DGS introduces a lightweight, deep Gaussian prior framework that enables efficient, high-quality image representation with minimal fine-tuning, significantly reducing computational costs compared to previous methods.

Contribution

We propose a novel Deep Gaussian Prior as a conditional network for efficient Gaussian image representation, enabling single-pass high-quality reconstruction with minimal fine-tuning.

Findings

Achieves high-quality image reconstruction in a single forward pass.

Reduces computational cost significantly compared to existing methods.

Maintains visual quality with minimal fine-tuning.

Abstract

As generative models become increasingly capable of producing high-fidelity visual content, the demand for efficient, interpretable, and editable image representations has grown substantially. Recent advances in 2D Gaussian Splatting (2DGS) have emerged as a promising solution, offering explicit control, high interpretability, and real-time rendering capabilities (>1000 FPS). However, high-quality 2DGS typically requires post-optimization. Existing methods adopt random or heuristics (e.g., gradient maps), which are often insensitive to image complexity and lead to slow convergence (>10s). More recent approaches introduce learnable networks to predict initial Gaussian configurations, but at the cost of increased computational and architectural complexity. To bridge this gap, we present Fast-2DGS, a lightweight framework for efficient Gaussian image representation. Specifically, we introduce Deep Gaussian Prior, implemented as a conditional network to capture the spatial distribution of Gaussian primitives under different complexities. In addition, we propose an attribute regression network to predict dense Gaussian properties. Experiments demonstrate that this disentangled architecture achieves high-quality reconstruction in a single forward pass, followed by minimal fine-tuning. More importantly, our approach significantly reduces computational cost without compromising visual quality, bringing 2DGS closer to industry-ready deployment.