HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning
This addresses a domain-specific issue for researchers and practitioners in image compression by improving model performance, though it is incremental as it builds on existing metrics and methods.
The paper tackles the problem of suboptimal model selection in learned image compression due to separate optimization for PSNR and MS-SSIM metrics by proposing HLIC, which uses reinforcement learning to harmonize these metrics, achieving better visual quality and higher VMAF scores.
Learned image compression is making good progress in recent years. Peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM) are the two most popular evaluation metrics. As different metrics only reflect certain aspects of human perception, works in this field normally optimize two models using PSNR and MS-SSIM as loss function separately, which is suboptimal and makes it difficult to select the model with best visual quality or overall performance. Towards solving this problem, we propose to Harmonize optimization metrics in Learned Image Compression (HLIC) using online loss function adaptation by reinforcement learning. By doing so, we are able to leverage the advantages of both PSNR and MS-SSIM, achieving better visual quality and higher VMAF score. To our knowledge, our work is the first to explore automatic loss function adaptation for harmonizing optimization metrics in low level vision tasks like learned image compression.