Edge-Aware Autoencoder Design for Real-Time Mixture-of-Experts Image Compression

TL;DR

This paper introduces an edge-aware autoencoder that significantly accelerates SMoE-based image compression, achieving real-time performance and improved quality by directly mapping pixel blocks to model parameters, bypassing iterative optimization.

Contribution

The novel autoencoder approach eliminates the need for iterative model-building in SMoE image compression, enabling real-time encoding with enhanced reconstruction quality.

Findings

Encoder run-time reduced by a factor of 500 to 1000.

Achieved real-time image compression performance.

Improved rate-distortion performance over previous methods.

Abstract

Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data. Recent works for image compression indicate that compression of images based on SMoE models can provide competitive performance to the state-of-the-art. Unfortunately, the iterative model-building process at the encoder comes with excessive computational demands. In this paper we introduce a novel edge-aware Autoencoder (AE) strategy designed to avoid the time-consuming iterative optimization of SMoE models. This is done by directly mapping pixel blocks to model parameters for compression, in spirit similar to recent works on "unfolding" of algorithms, while maintaining full compatibility to the established SMoE framework. With our plug-in AE encoder, we achieve a quantum-leap in performance with encoder run-time savings by a factor of 500 to 1000 with even improved image reconstruction quality. For image compression the plug-in AE encoder has real-time properties and improves RD-performance compared to our previous works.