用少量高斯点实现高效图像表示与压缩，速度更快、内存更低。
GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting
- 按信号强度动态分配高斯点，提升资源利用效率
- 在1080p下压缩率超40倍，重建误差低于0.75 dB
- 适合实时图像解码与低内存设备部署
隐式神经表示（INRs）在图像表征与压缩中表现优异，但训练耗时且内存开销大。近期基于2D高斯点渲染的方法（如GaussianImage）虽效率更高，却需大量高斯点维持视觉质量。为此，我们提出GaussianImage++，仅用有限高斯点即实现卓越的表征与压缩性能。首先，设计基于失真的密化机制，按信号强度动态分配高斯点；其次，引入上下文感知的高斯滤波器，根据图像内容优化点分布；最后，集成属性分离的可学习标量量化器与量化感知训练，实现对点属性的高效压缩。实验表明，GaussianImage++在1080p图像上压缩率超40倍，重建误差低于0.75 dB，优于GaussianImage与基于INR的COIN方法，同时支持实时解码与低内存运行。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。