英偉達公布AI黑科技！可生成超逼真人臉，還能神速修復受損照片

Can YOU spot the real person? Creepy AI can now create 『100 per cent lifelike』 human faces from scratch (as well as animals, cars and even bedrooms)

你能分辨出哪個是真人嗎？令人毛骨悚然的人工智慧現在可以從零開始創造出「100%逼真」的人臉（還有動物、汽車甚至卧室）

素材來源：每日郵報 翻譯：世界播

Can you tell who is real and who is not? Artificial Intelligence is now able to create lifelike human faces from scratch.

你能分辨出誰是真實的，誰不是真實的嗎？人工智慧現在能夠從頭開始創造出逼真的人臉。

Researchers at NVIDIA have been working on creating realistic looking human faces from only a few source photos for years.

多年來，英偉達公司的研究人員一直致力於從幾張源圖片中創造出逼真的人臉。

For many people it"s difficult to tell the difference between one of the faces generated below and an actual human face, can you spot which is which?

對於許多人來說，很難區分下面生成的一張臉和真實的人臉，你能分辨出哪個是哪個嗎？

The team at NVIDIA, released a paper on the subject, and explained they used Generative Adversarial Networks (GAN), to customise the realistic looking faces.

英偉達團隊發表了一篇關於這個主題的論文，並解釋說他們使用了生成對抗網路來定製逼真的面孔。

The fake faces can be easily customised by using a method known as "style transfer" which blends the characteristics of one image with another.

通過使用一種稱為「風格轉換」的方法，可以很容易地定製這些假面孔，這種方法將一張圖像的特徵與另一張圖像融合在一起。

The generator thinks of the image as a collection of three styles, known as coarse styles (pose, hair, face shape), middle styles (facial features and eyes) and fine styles (colour scheme).

生成器將圖像視為三種風格的集合，即粗糙風格（姿勢、頭髮、臉型）、中等風格（面部特徵和眼睛）和精細風格（配色方案）。

Animals, such as cats, and objects such as a bedroom can also be generated, using the same method.

也可以使用相同的方法生成動物（如貓）和物體（如卧室）。

The researchers created a grid to show the extent to which they could alter people"s facial characteristics using only one source image.

研究人員創建了一個網格來顯示他們僅使用一幅源圖像就可以改變人們面部特徵的程度。

One of the most fascinating aspects of this is GAN has only be around for four years.

最吸引人的一點是生成對抗網路方法是4年前才提出來的。

But, is it not yet perfect, there are giveaways that can indicate that you are looking at an AI image.

它還不夠完美，有露餡的地方，暗示你正在看的是一個AI圖像。

For example the hair is very difficult to replicate, and as such, can often looked painted on, or slightly peculiar.

例如，頭髮是很難複製的，以及其他像這樣的特徵，通常能看出來是被畫上去的，或略有古怪。

The advances in this technology also poses interesting ethical questions.

這項技術的進步也引發了有趣的倫理問題。

Can people really trust pictorial evidence?

圖片證據真的能相信嗎？

What are the implications for governments or repressive regimes being able to use this technology for propaganda or to spread misinformation?

政府或壓制性政權能夠利用這種技術進行宣傳或傳播假信息，這意味著什麼？

Earlier this year we revealed how Nvidia software uses AI and deep-learning algorithms to predict what a missing portion of a picture should look like and recreate it with incredible accuracy.

今年早些時候，我們揭示了英偉達軟體公司是如何使用人工智慧和深度學習演算法來預測一張圖片缺失的部分應該是什麼樣子的，並以驚人的準確性重建了它。

All users need to do is click and drag over the area to be filled in and the image is instantly updated.

所有用戶需要做的就是點擊並拖動需要填充的區域，圖像就會立即更新。

As well as restoring old physical photos that have been damaged, the technique could also be used to fix corrupted pixels or bad edits made to digital files.

除了修復損壞的舊照片，這項技術還可以用來修復損壞的像素或對數字文件的錯誤編輯。

Photoshop could become a thing of the past as new technology has been developed by Nvidia which can instantly improve touch-up damaged photos in seconds

英偉達開發出一種新技術，可以在幾秒鐘內迅速修復受損照片，Photoshop可能會成為過去

Graphics specialist Nvidia, based in Santa Clara, California trained its neural network using a variety of irregular shaped holes in images.

英偉達公司位於加州聖克拉拉，是圖形處理方面的專家，它使用圖像中各種形狀不規則的小孔對其神經網路進行了訓練。

The system then determined what was missing from each and filled in the gaps.

然後，系統確定每一項都缺少什麼，並填補空白。

喜歡這篇文章嗎？立刻分享出去讓更多人知道吧！