Publication
Generalized nested latent variable models for lossy coding applied to wind turbine scenarios
Conference Article
Conference
IEEE International Conference on Image Processing (ICIP)
Edition
2024
Pages
1947-1953
Doc link
http://dx.doi.org/10.1109/ICIP51287.2024.10648110
File
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
Categories
pattern recognition.
Author keywords
Image Compression, Rate-distortion Loss, Nested Models, Wind Turbine, Blade Inspections
Scientific reference
R. Pérez, A. Espersen and A. Agudo. Generalized nested latent variable models for lossy coding applied to wind turbine scenarios, 2024 IEEE International Conference on Image Processing, 2024, Abu Dhabi, UAE, pp. 1947-1953.
Follow us!