论文标题
视频压缩和低复杂性CNN基于CNN的空间分辨率适应
Video compression with low complexity CNN-based spatial resolution adaptation
论文作者
论文摘要
最近已经证明，可以在视频压缩中集成空间分辨率适应，以通过在解码器进行编码和超级分解之前通过空间下采样来提高整体编码性能。当使用卷积神经网络（CNN）来进行分辨率上采样时，已经报道了显着改善。但是，由于使用了基于CNN的超分辨率，这种方法在解码器上具有很高的复杂性。在本文中，提出了一个新颖的框架，该框架支持编码器和解码器之间复杂性的灵活分配。该方法采用CNN模型在编码器上进行视频下采样，并使用Lanczos3滤波器在解码器上重建完整分辨率。提出的方法集成到HEVC HM 16.20软件中，并使用所有内部配置在JVET UHD测试序列上进行评估。实验结果证明了所提出的方法的潜力，比原始HEVC HM的比特率节省明显（超过10％），并与Encoder（29％）和解码器（10％）的计算复杂性降低相结合。
It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder. Significant improvements have been reported when convolutional neural networks (CNNs) were used to perform the resolution up-sampling. However, this approach suffers from high complexity at the decoder due to the employment of CNN-based super-resolution. In this paper, a novel framework is proposed which supports the flexible allocation of complexity between the encoder and decoder. This approach employs a CNN model for video down-sampling at the encoder and uses a Lanczos3 filter to reconstruct full resolution at the decoder. The proposed method was integrated into the HEVC HM 16.20 software and evaluated on JVET UHD test sequences using the All Intra configuration. The experimental results demonstrate the potential of the proposed approach, with significant bitrate savings (more than 10%) over the original HEVC HM, coupled with reduced computational complexity at both encoder (29%) and decoder (10%).
