LVMark: Robust Watermark for Latent Video Diffusion Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915217240227840 |
|---|---|
| author | Jang, MinHyuk Jang, Youngdong Lee, JaeHyeok Yang, Feng Oh, Gyeongrok Jeong, Jongheon Kim, Sangpil |
| author_facet | Jang, MinHyuk Jang, Youngdong Lee, JaeHyeok Yang, Feng Oh, Gyeongrok Jeong, Jongheon Kim, Sangpil |
| contents | Rapid advancements in video diffusion models have enabled the creation of realistic videos, raising concerns about unauthorized use and driving the demand for techniques to protect model ownership. Existing watermarking methods, while effective for image diffusion models, do not account for temporal consistency, leading to degraded video quality and reduced robustness against video distortions. To address this issue, we introduce LVMark, a novel watermarking method for video diffusion models. We propose a new watermark decoder tailored for generated videos by learning the consistency between adjacent frames. It ensures accurate message decoding, even under malicious attacks, by combining the low-frequency components of the 3D wavelet domain with the RGB features of the video. Additionally, our approach minimizes video quality degradation by embedding watermark messages in layers with minimal impact on visual appearance using an importance-based weight modulation strategy. We optimize both the watermark decoder and the latent decoder of diffusion model, effectively balancing the trade-off between visual quality and bit accuracy. Our experiments show that our method embeds invisible watermarks into video diffusion models, ensuring robust decoding accuracy with 512-bit capacity, even under video distortions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09122 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LVMark: Robust Watermark for Latent Video Diffusion Models Jang, MinHyuk Jang, Youngdong Lee, JaeHyeok Yang, Feng Oh, Gyeongrok Jeong, Jongheon Kim, Sangpil Computer Vision and Pattern Recognition Rapid advancements in video diffusion models have enabled the creation of realistic videos, raising concerns about unauthorized use and driving the demand for techniques to protect model ownership. Existing watermarking methods, while effective for image diffusion models, do not account for temporal consistency, leading to degraded video quality and reduced robustness against video distortions. To address this issue, we introduce LVMark, a novel watermarking method for video diffusion models. We propose a new watermark decoder tailored for generated videos by learning the consistency between adjacent frames. It ensures accurate message decoding, even under malicious attacks, by combining the low-frequency components of the 3D wavelet domain with the RGB features of the video. Additionally, our approach minimizes video quality degradation by embedding watermark messages in layers with minimal impact on visual appearance using an importance-based weight modulation strategy. We optimize both the watermark decoder and the latent decoder of diffusion model, effectively balancing the trade-off between visual quality and bit accuracy. Our experiments show that our method embeds invisible watermarks into video diffusion models, ensuring robust decoding accuracy with 512-bit capacity, even under video distortions. |
| title | LVMark: Robust Watermark for Latent Video Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.09122 |