Prativadibhayankaram S, Panda MP, Richter T, Sparenberg H, Fosel S, Kaup A (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 3-12
Conference Proceedings Title: Data Compression Conference Proceedings
ISBN: 9798350385878
DOI: 10.1109/DCC58796.2024.00008
We propose the structure and color based learned image codec (SLIC) in which the task of compression is split into that of luminance and chrominance. The deep learning model is built with a novel multi-scale architecture for Y and UV channels in the encoder, where the features from various stages are combined to obtain the latent representation. An autoregressive context model is employed for backward adaptation and a hyperprior block for forward adaptation. Various experiments are carried out to study and analyze the performance of the proposed model, and to compare it with other image codecs. We also illustrate the advantages of our method through the visualization of channel impulse responses, latent channels and various ablation studies. The model achieves Bjontegaard delta bitrate gains of 7.5% and 4.66% in terms of MS-SSIM and CIEDE2000 metrics with respect to other state-of-the-art reference codecs.
APA:
Prativadibhayankaram, S., Panda, M.P., Richter, T., Sparenberg, H., Fosel, S., & Kaup, A. (2024). SLIC: A Learned Image Codec Using Structure and Color. In Ali Bilgin, James E. Fowler, Joan Serra-Sagrista, Yan Ye, James A. Storer (Eds.), Data Compression Conference Proceedings (pp. 3-12). Snowbird, UT, US: Institute of Electrical and Electronics Engineers Inc..
MLA:
Prativadibhayankaram, Srivatsa, et al. "SLIC: A Learned Image Codec Using Structure and Color." Proceedings of the 2024 Data Compression Conference, DCC 2024, Snowbird, UT Ed. Ali Bilgin, James E. Fowler, Joan Serra-Sagrista, Yan Ye, James A. Storer, Institute of Electrical and Electronics Engineers Inc., 2024. 3-12.
BibTeX: Download