3 papers
cs.MM2024
Fidelity-preserving Learning-Based Image Compression: Loss Function and Subjective Evaluation Methodology
Shima Mohammadi, Yaojun Wu, João Ascenso
Learning-based image compression methods have emerged as state-of-the-art, showcasing higher performance compared to conventional compression solutions. These data-driven approache…
cs.MM2023
Evaluation of Sampling Algorithms for a Pairwise Subjective Assessment Methodology
Shima Mohammadi, Joao Ascenso
Subjective assessment tests are often employed to evaluate image processing systems, notably image and video compression, super-resolution among others and have been used as an ind…
cs.MM2023
Perceptual impact of the loss function on deep-learning image coding performance
Shima Mohammadi, Joao Ascenso
Nowadays, deep-learning image coding solutions have shown similar or better compression efficiency than conventional solutions based on hand-crafted transforms and spatial predicti…