论文标题
PO-ELIC：面向感知的有效学到的图像编码
PO-ELIC: Perception-Oriented Efficient Learned Image Coding
论文作者
论文摘要
在过去的几年中，学到的图像压缩（LIC）取得了出色的性能。最近的LIC方法在PSNR和MS-SSIM中的表现都优于VVC。但是，LIC的低比率重建遭受了诸如模糊，颜色漂移和质地缺失等文物的影响。此外，这些不同的文物使图像质量指标与人类的感知质量密切相关。在本文中，我们提出了Po-eLIC，即面向感知的有效学习的图像编码。具体来说，我们采用了对抗性培训技术来适应最先进的LIC模型之一。我们将损失的混合物混合在一起，包括铰链形式的对抗损失，Charbonnier损失和样式损失，以确保模型以提高感知质量。实验结果表明，我们的方法具有可比的感知质量，而比特率较低。
In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate reconstructions of LIC suffer from artifacts such as blurring, color drifting and texture missing. Moreover, those varied artifacts make image quality metrics correlate badly with human perceptual quality. In this paper, we propose PO-ELIC, i.e., Perception-Oriented Efficient Learned Image Coding. To be specific, we adapt ELIC, one of the state-of-the-art LIC models, with adversarial training techniques. We apply a mixture of losses including hinge-form adversarial loss, Charbonnier loss, and style loss, to finetune the model towards better perceptual quality. Experimental results demonstrate that our method achieves comparable perceptual quality with HiFiC with much lower bitrate.
