Steered Mixture-of-Experts Autoencoder Design for Real-Time Image Modelling and Denoising

TL;DR

This paper introduces an improved autoencoder framework for Steered Mixture-of-Experts that enables fast, high-quality image modeling and denoising, suitable for real-time applications like compression and super-resolution.

Contribution

It extends previous autoencoder designs to support more complex models and various block sizes, significantly enhancing reconstruction quality and noise robustness.

Findings

Enables ultra-fast parameter estimation for complex SMoE models

Achieves high-quality image reconstruction in noise-free and noisy conditions

Broadens SMoE applications to compression, denoising, and super-resolution

Abstract

Research in the past years introduced Steered Mixture-of-Experts (SMoE) as a framework to form sparse, edge-aware models for 2D- and higher dimensional pixel data, applicable to compression, denoising, and beyond, and capable to compete with state-of-the-art compression methods. To circumvent the computationally demanding, iterative optimization method used in prior works an autoencoder design is introduced that reduces the run-time drastically while simultaneously improving reconstruction quality for block-based SMoE approaches. Coupling a deep encoder network with a shallow, parameter-free SMoE decoder enforces an efficent and explainable latent representation. Our initial work on the autoencoder design presented a simple model, with limited applicability to compression and beyond. In this paper, we build on the foundation of the first autoencoder design and improve the reconstruction quality by expanding it to models of higher complexity and different block sizes. Furthermore, we improve the noise robustness of the autoencoder for SMoE denoising applications. Our results reveal that the newly adapted autoencoders allow ultra-fast estimation of parameters for complex SMoE models with excellent reconstruction quality, both for noise free input and under severe noise. This enables the SMoE image model framework for a wide range of image processing applications, including compression, noise reduction, and super-resolution.