Generalized Nested Latent Variable Models For Lossy Coding Applied To Wind Turbine Scenarios
Year: 2024
Type: conference-paper
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.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Innovation Fund
OpenAlex ID: W4402916862