Neural Image Compression
Neural image compression uses deep learning to achieve superior rate-distortion performance compared to traditional methods, aiming to minimize data size while preserving image quality. Current research focuses on improving model efficiency and controllability, exploring architectures like variational autoencoders and transformers, often incorporating techniques such as predictive coding, adaptive quantization, and generative models to enhance both objective and perceptual fidelity. These advancements are significant for applications requiring efficient image storage and transmission, particularly in resource-constrained environments and for large-scale multimedia data management.
Papers
September 26, 2023
September 20, 2023
September 6, 2023
August 15, 2023
August 4, 2023
July 17, 2023
July 12, 2023
July 5, 2023
June 9, 2023
May 25, 2023
May 12, 2023
April 14, 2023
April 13, 2023
February 10, 2023
January 26, 2023
December 20, 2022
October 12, 2022
October 10, 2022
September 28, 2022