GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting

TL;DR

GaussianImage++ introduces a novel approach combining limited Gaussian primitives with adaptive densification and quantization techniques to significantly improve image representation and compression efficiency, outperforming previous methods while enabling real-time decoding.

Contribution

It presents a new GaussianImage++ method that uses adaptive Gaussian primitive allocation and attribute quantization for efficient image compression, surpassing prior GaussianImage and INR-based methods.

Findings

Outperforms GaussianImage and COIN in representation quality.

Maintains real-time decoding with low memory usage.

Uses adaptive densification and quantization for efficient primitives management.

Abstract

Implicit neural representations (INRs) have achieved remarkable success in image representation and compression, but they require substantial training time and memory. Meanwhile, recent 2D Gaussian Splatting (GS) methods (\textit{e.g.}, GaussianImage) offer promising alternatives through efficient primitive-based rendering. However, these methods require excessive Gaussian primitives to maintain high visual fidelity. To exploit the potential of GS-based approaches, we present GaussianImage++, which utilizes limited Gaussian primitives to achieve impressive representation and compression performance. Firstly, we introduce a distortion-driven densification mechanism. It progressively allocates Gaussian primitives according to signal intensity. Secondly, we employ context-aware Gaussian filters for each primitive, which assist in the densification to optimize Gaussian primitives based on varying image content. Thirdly, we integrate attribute-separated learnable scalar quantizers and quantization-aware training, enabling efficient compression of primitive attributes. Experimental results demonstrate the effectiveness of our method. In particular, GaussianImage++ outperforms GaussianImage and INRs-based COIN in representation and compression performance while maintaining real-time decoding and low memory usage.