DINVMark: A Deep Invertible Network for Video Watermarking

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ji, Jianbin, Xu, Dawen, Dong, Li, Yang, Lin, He, Songhan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915506422808576
author Ji, Jianbin
Xu, Dawen
Dong, Li
Yang, Lin
He, Songhan
author_facet Ji, Jianbin
Xu, Dawen
Dong, Li
Yang, Lin
He, Songhan
contents With the wide spread of video, video watermarking has become increasingly crucial for copyright protection and content authentication. However, video watermarking still faces numerous challenges. For example, existing methods typically have shortcomings in terms of watermarking capacity and robustness, and there is a lack of specialized noise layer for High Efficiency Video Coding(HEVC) compression. To address these issues, this paper introduces a Deep Invertible Network for Video watermarking (DINVMark) and designs a noise layer to simulate HEVC compression. This approach not only in creases watermarking capacity but also enhances robustness. DINVMark employs an Invertible Neural Network (INN), where the encoder and decoder share the same network structure for both watermark embedding and extraction. This shared architecture ensures close coupling between the encoder and decoder, thereby improving the accuracy of the watermark extraction process. Experimental results demonstrate that the proposed scheme significantly enhances watermark robustness, preserves video quality, and substantially increases watermark embedding capacity.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17416
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DINVMark: A Deep Invertible Network for Video Watermarking
Ji, Jianbin
Xu, Dawen
Dong, Li
Yang, Lin
He, Songhan
Cryptography and Security
With the wide spread of video, video watermarking has become increasingly crucial for copyright protection and content authentication. However, video watermarking still faces numerous challenges. For example, existing methods typically have shortcomings in terms of watermarking capacity and robustness, and there is a lack of specialized noise layer for High Efficiency Video Coding(HEVC) compression. To address these issues, this paper introduces a Deep Invertible Network for Video watermarking (DINVMark) and designs a noise layer to simulate HEVC compression. This approach not only in creases watermarking capacity but also enhances robustness. DINVMark employs an Invertible Neural Network (INN), where the encoder and decoder share the same network structure for both watermark embedding and extraction. This shared architecture ensures close coupling between the encoder and decoder, thereby improving the accuracy of the watermark extraction process. Experimental results demonstrate that the proposed scheme significantly enhances watermark robustness, preserves video quality, and substantially increases watermark embedding capacity.
title DINVMark: A Deep Invertible Network for Video Watermarking
topic Cryptography and Security
url https://arxiv.org/abs/2509.17416