Flexible Neural Image Compression via Code Editing
This addresses the practical deployment challenge of neural image compression for applications requiring flexible coding, though it is incremental in improving upon prior variable-rate approaches.
The paper tackles the inflexibility of neural image compression by proposing Code Editing, a method that enables variable bitrate control, ROI coding, and multi-distortion trade-offs with a single decoder, achieving superior performance over existing variable-rate methods.
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.