Spatially adaptive image compression using a tiled deep network
This work addresses the need for more efficient image compression by adapting bit rates spatially, offering incremental improvements over existing neural network methods.
The paper tackled the problem of spatially adaptive image compression by introducing a tiled deep network that adjusts bit rates based on local image complexity and visual saliency, resulting in improved PSNR and subjective ratings compared to non-adaptive and fully-convolutional baselines.
Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant spatial bit rate across each image. While entropy coding introduces some spatial variation, traditional codecs have benefited significantly by explicitly adapting the bit rate based on local image complexity and visual saliency. This paper introduces an algorithm that combines deep neural networks with quality-sensitive bit rate adaptation using a tiled network. We demonstrate the importance of spatial context prediction and show improved quantitative (PSNR) and qualitative (subjective rater assessment) results compared to a non-adaptive baseline and a recently published image compression model based on fully-convolutional neural networks.