Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion
This work addresses image compression for mobile and high-resolution display applications, offering an incremental improvement over existing methods.
The paper tackles the problem of compressing ultra high resolution images for mobile and high-resolution displays by proposing an adaptive downsampled dual-layer compression system that uses learned content-adaptive downsampling kernels and deep upsampling networks, achieving state-of-the-art performance in rate-distortion metrics.
Ultra high resolution (UHR) images are almost always downsampled to fit small displays of mobile end devices and upsampled to its original resolution when exhibited on very high-resolution displays. This observation motivates us on jointly optimizing operation pairs of downsampling and upsampling that are spatially adaptive to image contents for maximal rate-distortion performance. In this paper, we propose an adaptive downsampled dual-layer (ADDL) image compression system. In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer. For decompression the base layer is decoded and upconverted to the original resolution using a deep upsampling neural network, aided by the prior knowledge of the learned adaptive downsampling kernels. We restrict the downsampling kernels to the form of Gabor filters in order to reduce the complexity of filter optimization and also reduce the amount of side information needed by the decoder for adaptive upsampling. Extensive experiments demonstrate that the proposed ADDL compression approach of jointly optimized, spatially adaptive downsampling and upconversion outperforms the state of the art image compression methods.