Video: What does a 109-year-old movie look like after coloring and raise its resolution to 4K?


After succeeding in his first attempt to use AI in Raising the resolution of a classic short movie to 4K and a frame rate of 60fps, YouTuber decided Dennis Sheriaev To repeat the experiment, but this time with a 109-year-old movie that was taken in New York City in 1911, and he used publicly available neural networks to increase its accuracy to 4K, and increase the frame rate to 60 frames per second, and this time publishing the video after coloring using intelligence techniques Artificial.

As in his previous attempt, Dennis used frame updating using Google’s DAIN and Gigapixel AI technologies from Topaz Labs. He eventually got 4K resolution and a frame refresh rate of 60fps, then later worked to restore the sharpness of the video in his own undisclosed manner, then colored the film using DeOldify Neural to add colors automatically.

The result, as you can see in the video below, is a colorful HD clip of New York City over a hundred years ago.

You can check out the original classic movie in this video below.

What is interesting about this experiment is that the clip is relatively long with approximately eight minutes, unlike the first experiment for a short video. But the results as it was the first time around, it was very amazing, if you are not going to approximate the details. Perhaps the least good thing about this clip is the colors that look good in some areas and bad in other areas of the film.

Despite all this, the result is still stunning, considering that the entire film is based on the use of artificial intelligence and neural networks, meaning that it is fully automatic without any manual human intervention.


Please enter your comment!
Please enter your name here