计算机应用研究2024，Vol.41Issue(6)：1840-1844,5.DOI:10.19734/j.issn.1001-3695.2023.10.0433
基于可逆神经网络的神经辐射场水印
Watermarking for neural radiation fields by invertible neural network
摘要
Abstract
Aimin at the copyright problem surrounding 3 D models of neural radiation fields focused on implicit representation,this paper tackled this issue by considering the embedding and extraction of neural radiation field watermarks as inverse prob-lems of image transformations,and proposed a scheme for protecting the copyright of neural radiation fields using invertible neural network watermarking.This scheme utilized 2D image watermarking technology to safeguard 3D scenes.In the forward process of the invertible network,the watermark was embedded in the training image of the neural radiation field.In the re-verse process,the watermark was extracted from the image rendered by the neural radiation field.This ensured copyright pro-tection for both the neural radiation field and the 3D scene.However,the rendering process of the neural radiation field may result in the loss of watermark information.To address this,the paper introduced an image quality enhancement module.This module utilized a neural network to recover the rendered image and subsequently extract the watermark.Simultaneously,the watermark was embedded in each training image to train the neural radiation field.This enabled the extraction of watermark in-formation from multiple viewpoints.Experimental results demonstrate that the watermarking scheme outlined in this paper ef-fectively achieves copyright protection and highlights the feasibility of the proposed approach.关键词
可逆神经网络/数字水印/神经辐射场/渲染Key words
invertible neural network/digital watermarking/neural radiation field(NeRF)/rendering分类
信息技术与安全科学引用本文复制引用
孙文权,刘佳,董炜娜,陈立峰,钮可..基于可逆神经网络的神经辐射场水印[J].计算机应用研究,2024,41(6):1840-1844,5.基金项目
国家自然科学基金面上项目 （）
