Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noise
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_ | 1866910625869856768 |
|---|---|
| author | Huang, Qinglong Li, Haoran Liao, Yong Hao, Yanbin Zhou, Pengyuan |
| author_facet | Huang, Qinglong Li, Haoran Liao, Yong Hao, Yanbin Zhou, Pengyuan |
| contents | Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques. However, little research has been conducted on the issues of information confidentiality and security to NeRF, such as steganography. Existing NeRF steganography solutions have shortcomings in low steganography quality, model weight damage, and limited amount of steganographic information. This paper proposes Noise-NeRF, a novel NeRF steganography method employing Adaptive Pixel Selection strategy and Pixel Perturbation strategy to improve the quality and efficiency of steganography via trainable noise. Extensive experiments validate the state-of-the-art performances of Noise-NeRF on both steganography quality and rendering quality, as well as effectiveness in super-resolution image steganography. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01216 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noise Huang, Qinglong Li, Haoran Liao, Yong Hao, Yanbin Zhou, Pengyuan Computer Vision and Pattern Recognition Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques. However, little research has been conducted on the issues of information confidentiality and security to NeRF, such as steganography. Existing NeRF steganography solutions have shortcomings in low steganography quality, model weight damage, and limited amount of steganographic information. This paper proposes Noise-NeRF, a novel NeRF steganography method employing Adaptive Pixel Selection strategy and Pixel Perturbation strategy to improve the quality and efficiency of steganography via trainable noise. Extensive experiments validate the state-of-the-art performances of Noise-NeRF on both steganography quality and rendering quality, as well as effectiveness in super-resolution image steganography. |
| title | Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noise |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.01216 |