SDFVD2.0: Extension of Small Scale Deep Fake Video Dataset

The SDFVD 2.0 is an augmented extension of the original SDFVD dataset, which originally contained 53 real and 53 fake videos. This new version has been created to enhance the diversity and robustness of the dataset by applying various augmentation techniques like horizontal flip, rotation, shear, brightness and contrast adjustment, additive gaussian noise, downscaling and upscaling to the original videos. These augmentations help simulate a wider range of conditions and variations, making the dataset more suitable for training and evaluating deep learning models for deepfake detection. This process has significantly expanded the dataset resulting in 461 real and 461 forged videos, providing a richer and more varied collection of video data for deepfake detection research and development.
Dataset Structure
The dataset is organized into two main directories: real and fake, each containing the original and augmented videos. Each augmented video file is named following the pattern:
‘<prefix>_<original filename>_aug_<augmentation index>.mp4’
where <prefix> is either real or fake and <augmentation index> ranges from 0 to 7 corresponding to the different augmentation techniques applied.

SDFVD 2.0（SDFVD 2.0）是原始SDFVD数据集的增强扩展版本，原始数据集共包含53段真实视频与53段伪造视频。为提升数据集的多样性与鲁棒性，本新版本通过对原始视频应用多种数据增强技术进行构建，具体包括水平翻转、旋转、剪切、亮度与对比度调整、加性高斯噪声、下采样与上采样。此类增强操作可模拟更广泛的场景与变化条件，使该数据集更适用于深度伪造检测（deepfake detection）相关深度学习模型的训练与评估。经此扩充流程后，数据集规模得到显著提升，最终包含461段真实视频与461段伪造视频，为深度伪造检测的研究与开发提供了更为丰富多样的视频数据资源。

数据集结构
该数据集分为两个主要目录：real与fake，每个目录下均存放原始视频与增强后视频。每段增强视频的命名遵循如下格式：`<前缀（prefix）>_<原始文件名（original filename）>_aug_<增强索引（augmentation index）>.mp4`，其中`<前缀（prefix）>`的取值为real或fake，`<增强索引（augmentation index）>`的取值范围为0至7，分别对应所应用的不同增强技术。