GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting
This work addresses efficiency and fidelity issues in image compression for applications requiring fast processing, though it is incremental as it builds on existing Gaussian Splatting methods.
The paper tackles the problem of high computational cost in implicit neural representations and excessive primitives in 2D Gaussian Splatting for image representation and compression, achieving improved performance over GaussianImage and INRs-based COIN with real-time decoding and low memory usage.
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.