Spatially adaptive image compression using a tiled deep network

TL;DR

This paper presents a novel deep neural network-based image compression method that adaptively adjusts the spatial bit rate using a tiled network, leading to improved quality over non-adaptive models.

Contribution

It introduces a spatially adaptive image compression algorithm combining deep neural networks with quality-sensitive bit rate adaptation via tiling.

Findings

Improved PSNR compared to non-adaptive baseline.

Enhanced subjective visual quality.

Demonstrates the importance of spatial context prediction.

Abstract

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.