构建首个真实场景下的PRNU相机识别基准，提升识别精度。
PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification
- 用去噪自编码器+卷积网络混合架构估计PRNU信号
- 在13000张跨场景照片上实现1:120相机识别，性能超越当前最佳
- 首次采用哈达玛乘积设计，适合真实环境中的设备溯源
我们提出一个基于光电响应非均匀性（PRNU）的新型相机识别基准。该基准包含13,000张来自120多台相机拍摄的照片，训练与测试数据采样于不同场景，支持真实环境下的评估。同时，我们设计了一种新型PRNU相机识别模型，采用混合架构：先用去噪自编码器估计PRNU信号，再通过卷积网络实现1:N相机设备验证。不同于传统对比学习方法，该模型将参考与查询图像的PRNU信号进行哈达玛乘积作为输入，显著优于现有基于去噪自编码器和对比学习的先进模型。相关数据集与代码已开源：https://github.com/CroitoruAlin/PRNU-Bench。
原文摘要 · Abstract (English)
We propose a novel benchmark for camera identification via Photo Response Non-Uniformity (PRNU) estimation. The benchmark comprises 13K photos taken with 120+ cameras, where the training and test photos are taken in different scenarios, enabling ``in-the-wild'' evaluation. In addition, we propose a novel PRNU-based camera identification model that employs a hybrid architecture, comprising a denoising autoencoder to estimate the PRNU signal and a convolutional network that can perform 1:N verification of camera devices. Instead of using a conventional approach based on contrastive learning, our method takes the Hadamard product between reference and query PRNU signals as input. This novel design leads to significantly better results compared with state-of-the-art models based on denoising autoencoders and contrastive learning. We release our dataset and code at: https://github.com/CroitoruAlin/PRNU-Bench.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。