ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
This work addresses the problem of efficient and flexible image compression for practical deployment, particularly in low-bitrate scenarios, which is significant for applications requiring fast and efficient image transmission.
The authors tackled the problem of generative image compression with large-scale and rigid models, and their proposed method ProGIC achieved bitrate savings of up to 57.57% on DISTS and 58.83% on LPIPS, with over 10 times faster encoding and decoding. ProGIC enables progressive transmission and flexible deployment on low-bitrate scenarios.
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.