Generalized Nested Latent Variable Models for Lossy Coding applied to Wind Turbine Scenarios

TL;DR

This paper introduces a generalized nested latent variable model for lossy coding, demonstrating improved compression performance and reduced computational cost, specifically applied to wind turbine visual inspection scenarios.

Contribution

It extends existing hyperprior models to an L-level nested generative structure, optimizing compression and computational efficiency for wind turbine data.

Findings

Outperforms hyperprior models in compression quality

Reduces computational cost compared to existing methods

Effective in wind turbine visual inspection scenarios

Abstract

Rate-distortion optimization through neural networks has accomplished competitive results in compression efficiency and image quality. This learning-based approach seeks to minimize the compromise between compression rate and reconstructed image quality by automatically extracting and retaining crucial information, while discarding less critical details. A successful technique consists in introducing a deep hyperprior that operates within a 2-level nested latent variable model, enhancing compression by capturing complex data dependencies. This paper extends this concept by designing a generalized L-level nested generative model with a Markov chain structure. We demonstrate as L increases that a trainable prior is detrimental and explore a common dimensionality along the distinct latent variables to boost compression performance. As this structured framework can represent autoregressive coders, we outperform the hyperprior model and achieve state-of-the-art performance while reducing substantially the computational cost. Our experimental evaluation is performed on wind turbine scenarios to study its application on visual inspections