WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jang, Youngdong, Lee, Dong In, Jang, MinHyuk, Kim, Jong Wook, Yang, Feng, Kim, Sangpil
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911953140580352
author Jang, Youngdong
Lee, Dong In
Jang, MinHyuk
Kim, Jong Wook
Yang, Feng
Kim, Sangpil
author_facet Jang, Youngdong
Lee, Dong In
Jang, MinHyuk
Kim, Jong Wook
Yang, Feng
Kim, Sangpil
contents The advances in the Neural Radiance Fields (NeRF) research offer extensive applications in diverse domains, but protecting their copyrights has not yet been researched in depth. Recently, NeRF watermarking has been considered one of the pivotal solutions for safely deploying NeRF-based 3D representations. However, existing methods are designed to apply only to implicit or explicit NeRF representations. In this work, we introduce an innovative watermarking method that can be employed in both representations of NeRF. This is achieved by fine-tuning NeRF to embed binary messages in the rendering process. In detail, we propose utilizing the discrete wavelet transform in the NeRF space for watermarking. Furthermore, we adopt a deferred back-propagation technique and introduce a combination with the patch-wise loss to improve rendering quality and bit accuracy with minimum trade-offs. We evaluate our method in three different aspects: capacity, invisibility, and robustness of the embedded watermarks in the 2D-rendered images. Our method achieves state-of-the-art performance with faster training speed over the compared state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02066
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights
Jang, Youngdong
Lee, Dong In
Jang, MinHyuk
Kim, Jong Wook
Yang, Feng
Kim, Sangpil
Computer Vision and Pattern Recognition
Image and Video Processing
The advances in the Neural Radiance Fields (NeRF) research offer extensive applications in diverse domains, but protecting their copyrights has not yet been researched in depth. Recently, NeRF watermarking has been considered one of the pivotal solutions for safely deploying NeRF-based 3D representations. However, existing methods are designed to apply only to implicit or explicit NeRF representations. In this work, we introduce an innovative watermarking method that can be employed in both representations of NeRF. This is achieved by fine-tuning NeRF to embed binary messages in the rendering process. In detail, we propose utilizing the discrete wavelet transform in the NeRF space for watermarking. Furthermore, we adopt a deferred back-propagation technique and introduce a combination with the patch-wise loss to improve rendering quality and bit accuracy with minimum trade-offs. We evaluate our method in three different aspects: capacity, invisibility, and robustness of the embedded watermarks in the 2D-rendered images. Our method achieves state-of-the-art performance with faster training speed over the compared state-of-the-art methods.
title WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2405.02066