close

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 settingshugging, talking, expressing emotion and the like. To transform their faces, Google used publicly available, state-of-the-art, automatic deepfake algorithmsDeepfakes, 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。

arrow
arrow
    全站熱搜
    創作者介紹
    創作者 ests24331677 的頭像
    ests24331677

    【精英翻譯】的部落格

    ests24331677 發表在 痞客邦 留言(0) 人氣()