Flexible Neural Image Compression via Code Editing

TL;DR

This paper introduces Code Editing, a flexible neural image compression method that enables variable bitrate control and multi-distortion trade-offs with a single decoder, surpassing existing methods in performance.

Contribution

It presents a novel paradigm for variable bitrate neural image compression using semi-amortized inference and adaptive quantization, overcoming limitations of prior conditional coding approaches.

Findings

Outperforms existing variable-rate methods in rate-distortion performance.

Enables ROI coding and multi-distortion trade-offs with a single decoder.

Provides a flexible and practical approach for neural image compression.

Abstract

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.