A generic postprocessing technique for image compression

Abstract

A postprocessing approach is developed for image coding applications. In this approach, a distortion-recovery model extracts multi-resolution edge features from the decompressed image and uses these visual features as input to estimate the difference image between the original uncompressed image and the decompressed image. Coding distortions are directly compensated by adding the model output to the decompressed image. Unlike the majority of existing postprocessing methods, which adopt filtering techniques to smooth blocking artifacts and are designed specifically for transform coding or vector quantization, the proposed approach is a generic postprocessing technique and can be applied to all of the main coding methods. Experiments involving postprocessing four coding systems were conducted, and the results obtained show that the proposed technique achieves significant improvements on the quality of reconstructed images, both in terms of the objective distortion measure and subjective visual assessment.

More information

Identifiers

Catalogue record

Export record