Abstract
Recent advances in generative image compression (GIC) have delivered remarkable improvements in perceptual quality. However, many GICs rely on large-scale and rigid models, which severely constrain their utility for flexible transmission and practical deployment in low-bitrate scenarios. To address these issues, we propose Progressive Generative Image Compression (ProGIC), a compact codec built on residual vector quantization (RVQ). In RVQ, a sequence of vector quantizers encodes the residuals stage by stage, each with its own codebook. The resulting codewords sum to a coarse-to-fine reconstruction and a progressive bitstream, enabling previews from partial data. We pair this with a lightweight backbone based on depthwise-separable convolutions and small attention blocks, enabling practical deployment on both GPUs and CPU-only devices. Experimental results show that ProGIC attains comparable compression performance compared with previous methods. It achieves bitrate savings of up to 57.57% on DISTS and 58.83% on LPIPS compared to MS-ILLM on the Kodak dataset. Beyond perceptual quality, ProGIC enables progressive transmission for flexibility, and also delivers over 10 times faster encoding and decoding compared with MS-ILLM on GPUs for efficiency.
Abstract (translated)
最近在生成图像压缩（GIC）领域取得的进展显著提升了感知质量。然而，许多现有的GIC方法依赖于大规模且刚性的模型架构，这严重限制了它们在网络传输中的灵活性和在低比特率场景下的实际部署能力。为了解决这些问题，我们提出了渐进式生成图像压缩（ProGIC），这是一种基于残差向量量化（RVQ）构建的紧凑型编解码器。 在RVQ中，一系列向量量化器依次编码残差数据，每个量化器都有自己的代码本。这种机制产生了从粗糙到精细的重建结果和渐进式的比特流，从而允许使用部分数据进行预览。我们还采用了一种基于可分离深度卷积和小注意力模块构建的轻量级骨干网络，这使得ProGIC能够在支持GPU设备的同时，也能在仅CPU设备上实际部署。 实验结果显示，与先前的方法相比，ProGIC实现了相仿的压缩性能。具体而言，在Kodak数据集上的DISTS指标下，它比MS-ILLM方法节省了高达57.57%的比特率；而在LPIPS指标下，则节省了58.83%。此外，除了感知质量之外，ProGIC还支持渐进式传输以增强灵活性，并且在GPU上的编码和解码速度上比MS-ILLM快超过10倍，从而大大提高了效率。
URL
https://arxiv.org/abs/2603.02897
