Neural Image Compression with Quantization Rectifier
CoRR(2024)
摘要
Neural image compression has been shown to outperform traditional image
codecs in terms of rate-distortion performance. However, quantization
introduces errors in the compression process, which can degrade the quality of
the compressed image. Existing approaches address the train-test mismatch
problem incurred during quantization, the random impact of quantization on the
expressiveness of image features is still unsolved. This paper presents a novel
quantization rectifier (QR) method for image compression that leverages image
feature correlation to mitigate the impact of quantization. Our method designs
a neural network architecture that predicts unquantized features from the
quantized ones, preserving feature expressiveness for better image
reconstruction quality. We develop a soft-to-predictive training technique to
integrate QR into existing neural image codecs. In evaluation, we integrate QR
into state-of-the-art neural image codecs and compare enhanced models and
baselines on the widely-used Kodak benchmark. The results show consistent
coding efficiency improvement by QR with a negligible increase in the running
time.
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