Super-High-Fidelity Image Compression via Hierarchical-ROI and Adaptive Quantization
arxiv(2024)
摘要
Learned Image Compression (LIC) has achieved dramatic progress regarding
objective and subjective metrics. MSE-based models aim to improve objective
metrics while generative models are leveraged to improve visual quality
measured by subjective metrics. However, they all suffer from blurring or
deformation at low bit rates, especially at below 0.2bpp. Besides,
deformation on human faces and text is unacceptable for visual quality
assessment, and the problem becomes more prominent on small faces and text. To
solve this problem, we combine the advantage of MSE-based models and generative
models by utilizing region of interest (ROI). We propose Hierarchical-ROI
(H-ROI), to split images into several foreground regions and one background
region to improve the reconstruction of regions containing faces, text, and
complex textures. Further, we propose adaptive quantization by non-linear
mapping within the channel dimension to constrain the bit rate while
maintaining the visual quality. Exhaustive experiments demonstrate that our
methods achieve better visual quality on small faces and text with lower bit
rates, e.g., 0.7X bits of HiFiC and 0.5X bits of BPG.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要