TY - JOUR
AU1 - Ladune, Théo
AU2 - Philippe, Pierrick
AU3 - Clare, Gordon
AU4 - Henry, Félix
AU5 - Leguay, Thomas
AB - Abstract:This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight image decoders while still offering competitive performance. The approach is based on the already published overfitted lightweight neural networks Cool-Chic, further adapted to the human subjective viewing targeted in this challenge.
TI - Cool-Chic: Perceptually Tuned Low Complexity Overfitted Image Coder
JF - Electrical Engineering and Systems Science
DO - 10.48550/arxiv.2401.02156
DA - 2024-01-04
UR - https://www.deepdyve.com/lp/arxiv-cornell-university/cool-chic-perceptually-tuned-low-complexity-overfitted-image-coder-pc0JNmNZFK
VL - 2024
IS - 2401
DP - DeepDyve
ER -