Abstract
Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However, many existing approaches achieve high rate-distortion efficiency at the expense of increased computational cost and limited parallelism. This paper presents ARCHE - Autoregressive Residual Compression with Hyperprior and Excitation, an end-to-end learned image compression framework that balances modeling accuracy and computational efficiency. The proposed architecture unifies hierarchical, spatial, and channel-based priors within a single probabilistic framework, capturing both global and local dependencies in the latent representation of the image, while employing adaptive feature recalibration and residual refinement to enhance latent representation quality. Without relying on recurrent or transformer-based components, ARCHE attains state-of-the-art rate-distortion efficiency: it reduces the BD-Rate by approximately 48% relative to the commonly used benchmark model of Balle et al., 30% relative to the channel-wise autoregressive model of Minnen & Singh and 5% against the VVC Intra codec on the Kodak benchmark dataset. The framework maintains computational efficiency with 95M parameters and 222ms running time per image. Visual comparisons confirm sharper textures and improved color fidelity, particularly at lower bit rates, demonstrating that accurate entropy modeling can be achieved through efficient convolutional designs suitable for practical deployment.
Abstract (translated)
最近基于学习的图像压缩研究显示，端到端优化可以通过联合学习紧凑的潜在表示和概率熵模型，在很大程度上超越传统编解码器。然而，许多现有的方法通过增加计算成本和有限的并行性来实现高率失真效率。本文介绍了一种名为ARCHE（自回归残差压缩与超前量和激励）的端到端学习图像压缩框架，该框架平衡了建模精度和计算效率。所提出的架构将层次化、空间性和通道级别的先验统一在一个概率框架内，捕捉到了图像潜在表示中的全局和局部依赖关系，并通过采用自适应特征再校准和残差细化来提高潜在表示的质量。在不依赖递归或基于变换器的组件的情况下，ARCHE达到了最先进的率失真效率：它将相对于Balle等人常用的基准模型减少了约48%的BD-Rate（比特率差异），比Minnen & Singh提出的通道级别的自回归模型减少了30%，以及比VVC Intra编解码器在Kodak基准数据集上减少了5%。该框架以95M参数和每张图片222ms的运行时间保持计算效率。视觉比较确认了纹理更清晰、颜色保真度更高的优势，特别是在较低比特率下，证明通过适合实际部署的有效卷积设计可以实现准确的概率模型化。
URL
https://arxiv.org/abs/2603.10188
