论文标题
通过代码编辑的灵活神经图像压缩
Flexible Neural Image Compression via Code Editing
论文作者
论文摘要
神经图像压缩（NIC）的表现优于传统图像编解码器（R-D）性能。但是，它通常需要R-D曲线上每个点的专用编码器对，这极大地阻碍了其实际部署。尽管最近的一些作品通过有条件的编码实现了比特率控制，但在培训期间，它们具有强大的先验性，并提供了有限的灵活性。在本文中，我们提出了代码编辑，这是一种基于半损坏的推理和自适应量化的NIC的高度灵活的编码方法。我们的工作是可变比特率NIC的新范式。此外，实验结果表明，我们的方法超过了现有的可变速率方法，并通过单个解码器实现了ROI编码和多功能权衡。
Neural image compression (NIC) has outperformed traditional image codecs in rate-distortion (R-D) performance. However, it usually requires a dedicated encoder-decoder pair for each point on R-D curve, which greatly hinders its practical deployment. While some recent works have enabled bitrate control via conditional coding, they impose strong prior during training and provide limited flexibility. In this paper we propose Code Editing, a highly flexible coding method for NIC based on semi-amortized inference and adaptive quantization. Our work is a new paradigm for variable bitrate NIC. Furthermore, experimental results show that our method surpasses existing variable-rate methods, and achieves ROI coding and multi-distortion trade-off with a single decoder.
