GaussianImage++：基于二维高斯泼溅的增强图像表示与压缩方法 (GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting)

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.

翻译：隐式神经表示（INRs）在图像表示与压缩领域取得了显著成功，但其训练时间和内存开销较大。与此同时，最近的二维高斯泼溅（GS）方法（例如GaussianImage）通过基于图元的高效渲染提供了有前景的替代方案。然而，这些方法需要过量的高斯图元以维持高视觉保真度。为充分挖掘基于GS方法的潜力，本文提出GaussianImage++，该方法利用有限的高斯图元实现了出色的表示与压缩性能。首先，我们引入一种失真驱动的致密化机制，该机制根据信号强度逐步分配高斯图元。其次，我们为每个图元采用上下文感知的高斯滤波器，这些滤波器辅助致密化过程，以根据不同的图像内容优化高斯图元。第三，我们集成了属性分离的可学习标量量化器与量化感知训练，从而实现对图元属性的高效压缩。实验结果验证了本方法的有效性。特别地，GaussianImage++在表示与压缩性能上均优于GaussianImage和基于INRs的COIN方法，同时保持了实时解码与低内存占用的优势。