轻量级生成式图像压缩，支持渐进传输与快速编解码
ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
- 基于残差向量量化实现分阶段编码，生成渐进比特流
- 在Kodak数据集上比MS-ILLM节省57.57%比特率（DISTS）
- 适合低延迟部署，编码解码速度超MS-ILLM 10倍以上
生成式图像压缩（GIC）近年来显著提升了感知质量，但多数方法依赖大规模、僵化的模型，限制了其在低比特率场景下的灵活传输与实际部署。为此，我们提出一种轻量级的渐进式生成式图像压缩（ProGIC），基于残差向量量化（RVQ）。在RVQ中，一系列向量量化器逐级编码残差，每个阶段拥有独立码本，生成的码字累加实现从粗到细的重建与渐进比特流，支持部分数据预览。我们采用基于深度可分离卷积和小注意力模块的轻量骨干网络，可在GPU和仅CPU设备上高效部署。实验表明，ProGIC在压缩性能上与先前方法相当：在Kodak数据集上，相比MS-ILLM，DISTS指标下比特率降低57.57%，LPIPS指标下降低58.83%。此外，它不仅支持渐进传输提升灵活性，还在GPU上实现超过10倍于MS-ILLM的编码解码速度，显著提升效率。
原文摘要 · Abstract (English)
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.
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。