Advances in media compression indicate significant potential to drive future media coding standards, e.g., Joint Photographic Experts Group's learning-basedimagecoding technologies (JPEG AI) and Joint Video Expe...
详细信息
ISBN:
(纸本)9781728185514
Advances in media compression indicate significant potential to drive future media coding standards, e.g., Joint Photographic Experts Group's learning-basedimagecoding technologies (JPEG AI) and Joint Video Experts Team's (JVET) deep neural networks (DNN) based video coding. These codecs in fact represent a new type of media format. As a dire consequence, traditional media security and forensic techniques will no longer be of use. This paper proposes an initial study on the effectiveness of traditional watermarking on two state-of-the-art learning based image coding. Results indicate that traditional watermarking methods are no longer effective. We also examine the forensic trails of various DNN architectures in the learningbased codecs by proposing a residual noise based source identification algorithm that achieved 79% accuracy.
End-to-end trainable models have reached the performance of traditional handcrafted compression techniques on videos and images. Since the parameters of these models are learned over large training sets, they are not ...
详细信息
ISBN:
(纸本)9781665492577
End-to-end trainable models have reached the performance of traditional handcrafted compression techniques on videos and images. Since the parameters of these models are learned over large training sets, they are not optimal for any given image to be compressed. In this paper, we propose an instance-based fine-tuning of a subset of decoder's bias to improve the reconstruction quality in exchange for extra encoding time and minor additional signaling cost. The proposed method is applicable to any end-to-end compression methods, improving the state-of-the-art neural image compression BD-rate by 3 - 5%.
暂无评论