论文标题
CAESR：有条件的自动编码器和超级分辨率，用于学习的空间可伸缩性
CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability
论文作者
论文摘要
在本文中，我们提出了CAESR，这是一种基于多功能视频编码（VVC）标准的基于混合学习的编码方法。我们的框架认为，用VVC Intra Intra Intromode编码的低分辨率信号为基层（BL），而具有HyperPrior（AE-HP）的深度有条件自动编码器为增强层（EL）模型。 EL编码器作为输入既具有升级的BL重建和原始图像。我们的方法依赖于有条件的编码，该编码了解了源的最佳混合物和高尺度的BL图像，从而使性能比残留的编码更好。在解码器侧，超分辨率（SR）模块用于恢复高分辨率的详细信息并颠倒条件编码过程。实验结果表明，我们的解决方案在可扩展的同时与VVC全分辨率内部编码具有竞争力。
In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.
