Facebook 的人工智慧AI找到了從影片中直接擷取人物動作的方法

Facebook的一組AI研究人員發表了一篇論文,內文描述一種能夠從真實世界影片中擷取人物動態畫面的技術。

這個技術目前稱為”Vid2Game”,由兩個AI人工智慧技術合成,第一個為”Pose2Pose”,這個技術是控制信號的輸入源(例如操縱桿或是遊戲手把的控制信號),來操縱給予方向以及姿勢,第二個為”Pose2Frame”,給固定背景圖像生成高解析度的輸出(也可以是動態的)。

 

論文的結論敘述,這種基於人工智慧的技術可以導致不同類型的遊戲”更為逼真且個性化”。


In this work, we develop a novel method for extracting a character from an uncontrolled video sequence and then reanimating it, on any background, according to a 2D control signal. Our method is able to create long sequences of coarsely-controlled poses in an autoregressive manner.
These poses are then converted into a video sequence by a second network, in a way that enables the careful handling and replacement of the background, which is crucial for many applications. Our work paves the way for new types of realistic and personalized games, which can be casually created from everyday videos. In addition, controllable characters extracted from YouTube-like videos can find their place in the virtual worlds and augmented realities.


完整的論文可以在紐約伊薩卡州的私立研究型康奈爾大學的官方網站上閱讀。

更多【EXP.GG TECH】消息:

要價 60 萬元!微軟展示世界最巨大的平板電腦
說好的 20 萬次呢?要 8 萬的三星 Fold 摺疊機才一天就傳出災情

Related Posts