UI-LIC: A Unified Framework for Evaluating Learned Image Compression Models
2026-06-22 • Multimedia
Multimedia
AI summaryⓘ
The authors created UI-LIC, an easy-to-use software tool that helps researchers compare different learned image compression models fairly and clearly. It combines six strong models and lets users train, test, and analyze them using the same settings. The tool also includes a simple interface to see how these new models stack up against traditional image compression methods by measuring quality and file size. Additionally, it offers interactive visuals to better understand where image quality changes. This framework is open-source, making it easier for others to study and improve image compression.
learned image compressionimage quality metricsPSNRSSIMVMAFLPIPSGUIopen-source softwarevideo intra-frame encoders
Authors
Nicholas J. Nolen, Luc Trudeau, Andrew C. Freeman
Abstract
The evaluation and comparison of Learned Image Compression (LIC) systems is complicated by heterogeneous software stacks, varying training conditions, and divergent evaluation methodologies. To address these challenges, we introduce UI-LIC, an open-source software framework for evaluating LIC models. We integrate six high-performance LIC models, and provide a centralized controller for performing training, inference, and analysis with shared configuration parameters. Our GUI program offers a streamlined interface to evaluate these models alongside traditional video intra-frame encoders, equalizing the compressed bitrates and calculating quality metrics such as PSNR, SSIM, VMAF, and LPIPS. Finally, we provide an interactive image analyzer with configurable quality heatmap overlays. Our framework lowers barriers to further LIC research, unlocking comparative metrics and subjective analysis with a single setup command. The open-source software is released under the MIT license and is available at github.com/BaylorMultimediaLab/UI-LIC.