Lightweight Multitask Learning for Robust JND Prediction using Latent Space and Reconstructed Frames
The Just Noticeable Difference (JND) refers to the smallest distortion in an image or video
that can be perceived by Human Visual System (HVS), and is widely used in optimizing …
that can be perceived by Human Visual System (HVS), and is widely used in optimizing …
Channel-wise Feature Decorrelation for Enhanced Learned Image Compression
F Pakdaman, M Gabbouj - IEEE Signal Processing Letters, 2024 - ieeexplore.ieee.org
The emerging Learned Compression (LC) replaces the traditional codec modules with Deep
Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This …
Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This …
Generalized Nested Latent Variable Models for Lossy Coding applied to Wind Turbine Scenarios
R Pérez-Gonzalo, A Espersen, A Agudo - arXiv preprint arXiv:2406.06165, 2024 - arxiv.org
Rate-distortion optimization through neural networks has accomplished competitive results
in compression efficiency and image quality. This learning-based approach seeks to …
in compression efficiency and image quality. This learning-based approach seeks to …
Joint End-to-End Image Compression and Denoising: Leveraging Contrastive Learning and Multi-Scale Self-ONNs
Y Xie, L Yu, F Pakdaman, M Gabbouj - arXiv preprint arXiv:2402.05582, 2024 - arxiv.org
Noisy images are a challenge to image compression algorithms due to the inherent difficulty
of compressing noise. As noise cannot easily be discerned from image details, such as high …
of compressing noise. As noise cannot easily be discerned from image details, such as high …
Perceptual Learned Image Compression via End-to-End JND-Based Optimization
Emerging Learned image Compression (LC) achieves significant improvements in coding
efficiency by end-to-end training of neural networks for compression. An important benefit of …
efficiency by end-to-end training of neural networks for compression. An important benefit of …
Image compression with learned lifting-based DWT and learned tree-based entropy models
UB Sahin, F Kamisli - Multimedia Systems, 2023 - Springer
This paper explores learned image compression based on traditional and learned discrete
wavelet transform (DWT) architectures and learned entropy models for coding DWT …
wavelet transform (DWT) architectures and learned entropy models for coding DWT …