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.

通过结合 MSE-based 模型和生成模型中感兴趣区域 (ROI) 的优势，我们提出了分层感兴趣区域 (H-ROI) 方法，将图像分为几个前景区域和一个背景区域，以提高包含人脸、文字和复杂纹理的区域的重建效果；进一步，通过通道维度内的非线性映射提出了自适应量化来限制比特率同时保持视觉质量。大量实验证明了我们方法在小脸和文字上以更低的比特率实现了更好的视觉质量，如 HiFiC 的 0.7X 比特和 BPG 的 0.5X 比特。