Google made thousands of deepfakes to aid detection efforts 谷歌製作數千部「深度偽造」影片 助力辨識造假影像
精英翻譯社轉自https://features.ltn.com.tw/english/article/paper/1326116
◎劉宜庭
Google has released a data set of thousands of deepfake videos that it produced using paid, consenting actors in order to help researchers in the ongoing work of coming up with detection methods.
谷歌已釋出一個內有數千部「深度偽造」影片的資料集,相關影像獲得付費演員同意產出,以協助研究者進行「深偽影片」辨識方法的研究。
The data set, available on Github, contains more than 3,000 deepfake videos. To produce the videos, Google used 28 actors, placing pairs of them in quotidian settings:hugging, talking, expressing emotion and the like. To transform their faces, Google used publicly available, state-of-the-art, automatic deepfake algorithms:Deepfakes, Face2Face, FaceSwap and NeuralTextures.
這個資料集裡有超過3000部「深度偽造」影片,可透過(軟體開發平台)GitHub取得。為了製作這些影像,谷歌僱用28名演員,兩兩拍攝他們的日常動作:擁抱、交談、表達情緒等。谷歌使用可公開取得、最先進的自動化深偽演算法:「Deepfakes」、「Face2Face」、「FaceSwap」、「NeuralTextures」來改變演員的臉部。
Earlier this month, Facebook just announced that it was launching a $10m deepfake detection project.
本月初,臉書甫宣布推出一項價值1000萬美元的深偽辨識專案。
留言列表