We introduce EGIC, a novel generative image compression method that allows
traversing the distortion-perception curve efficiently from a single model.
Specifically, we propose an implicitly encoded variant of image interpolation
that predicts the residual between a MSE-optimized and GAN-optimized decoder
output. On the receiver side, the user can then control the impact of the
residual on the GAN-based reconstruction. Together with improved GAN-based
building blocks, EGIC outperforms a wide-variety of perception-oriented and
distortion-oriented baselines, including HiFiC, MRIC and DIRAC, while
performing almost on par with VTM-20.0 on the distortion end. EGIC is simple to
implement, very lightweight (e.g. 0.18x model parameters compared to HiFiC) and
provides excellent interpolation characteristics, which makes it a promising
candidate for practical applications targeting the low bit range.

本研究提出了一种新的生成图像压缩方法：EGIC。该方法能够从单一模型有效地穿越失真 - 感知曲线，并提出了一种隐式编码的图像插值变体，通过预测均方误差优化和 GAN 优化解码器输出之间的残差来控制基于 GAN 的重建结果，性能优于多种以感知或失真为导向的比较方法，并几乎与失真端的 VTM-20.0 相媲美。EGIC 实现简单、非常轻量级，并具有出色的插值特性，是应用于低比特范围的实际应用中有很大潜力的候选方法。