MarkNeRF:Watermarking for Neural Radiance Field  

作　　者：Lifeng Chen Jia Liu Wenquan Sun Weina Dong Xiaozhong Pan 

机构地区：[1]Cryptographic Engineering Department,Institute of Cryptographic Engineering,Engineering University of PAP,Xi’an,710086,China [2]Key Laboratory of Network and Information Security of PAP,Xi’an,710086,China

出　　处：《Computers, Materials & Continua》2024年第7期1235-1250,共16页计算机、材料和连续体（英文）

基　　金：supported by the National Natural Science Foundation of China,with Fund Number 62272478.

摘　　要：This paper presents a novel watermarking scheme designed to address the copyright protection challenges encountered with Neural radiation field(NeRF)models.We employ an embedding network to integrate the watermark into the images within the training set.Then,theNeRFmodel is utilized for 3Dmodeling.For copyright verification,a secret image is generated by inputting a confidential viewpoint into NeRF.On this basis,design an extraction network to extract embedded watermark images fromconfidential viewpoints.In the event of suspicion regarding the unauthorized usage of NeRF in a black-box scenario,the verifier can extract the watermark from the confidential viewpoint to authenticate the model’s copyright.The experimental results demonstrate not only the production of visually appealing watermarks but also robust resistance against various types of noise attacks,thereby substantiating the effectiveness of our approach in safeguarding NeRF.

关 键 词：Neural radiation field 3D watermark ROBUSTNESS black box 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]