Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting

TL;DR

This paper introduces a fast, adaptable image representation method using 2D Gaussian Splatting that reduces training time and dynamically adjusts complexity, matching or surpassing previous methods in quality.

Contribution

It presents a novel self-adaptive Gaussian Splatting framework that significantly accelerates training and improves flexibility over prior GaussianImage techniques.

Findings

Reduces training time by up to tenfold.

Achieves comparable or better rendering quality.

Dynamically adjusts Gaussian points based on image complexity.

Abstract

Implicit Neural Representation (INR) has demonstrated remarkable advances in the field of image representation but demands substantial GPU resources. GaussianImage recently pioneered the use of Gaussian Splatting to mitigate this cost, however, the slow training process limits its practicality, and the fixed number of Gaussians per image limits its adaptability to varying information entropy. To address these issues, we propose in this paper a generalizable and self-adaptive image representation framework based on 2D Gaussian Splatting. Our method employs a network to quickly generate a coarse Gaussian representation, followed by minimal fine-tuning steps, achieving comparable rendering quality of GaussianImage while significantly reducing training time. Moreover, our approach dynamically adjusts the number of Gaussian points based on image complexity to further enhance flexibility and efficiency in practice. Experiments on DIV2K and Kodak datasets show that our method matches or exceeds GaussianImage's rendering performance with far fewer iterations and shorter training times. Specifically, our method reduces the training time by up to one order of magnitude while achieving superior rendering performance with the same number of Gaussians.