Steered mixture-of-experts autoencoder design for real-time image modelling and denoising

Elvira Fleig; Erik Bochinski; Thomas Sikora

doi:10.1117/12.2667082

7 June 2023 Steered mixture-of-experts autoencoder design for real-time image modelling and denoising

Elvira Fleig, Erik Bochinski, Thomas Sikora

Proceedings Volume 12571, Real-time Processing of Image, Depth and Video Information 2023; 125710K (2023) https://doi.org/10.1117/12.2667082
Event: SPIE Optics + Optoelectronics, 2023, Prague, Czech Republic

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.

Conference Presentation

Citation Download Citation

Elvira Fleig, Erik Bochinski, and Thomas Sikora "Steered mixture-of-experts autoencoder design for real-time image modelling and denoising", Proc. SPIE 12571, Real-time Processing of Image, Depth and Video Information 2023, 125710K (7 June 2023); https://doi.org/10.1117/12.2667082

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available