AI/ML

Adobe brings content-aware fill for videos to After Effects





Adobe today announced that it is bringing content-aware fill to After Effects, the special effects software that is part of its Creative Cloud offering. The company has long offered this feature in Photoshop, where you can use it to automatically remove objects from a photo, with the application filling in the blank space with appropriate pixels, based on what’s around it. As you can imagine, doing this for a video is significantly harder because you have to do this for every image while the objects move.

The company notes that this new feature is powered by Adobe Sensei, the company’s AI platform. To remove an object (or maybe a stray boom mic) from a scene is to mask it. If everything works as planned, the tools will automatically track the object through a scene (even when it moves behind another object for a bit) and replace it with more suitable pixels. If you need to fine-tune the result, you can also use Photoshop to create reference frames.

Adobe notes that content-aware fill is also a very useful tool for 360-degree VR projects, where you can’t always hide everything around the camera.

With the annual NAB show coming up next week, Adobe is also launching a plethora of other video updates for both After Effects and Premiere Pro. Some of those focus on workflow improvement, including the new Freeform Project panel that lets you arrange assets visually and improved audio tools (which now also feature Auto Ducking for ambient sound in Audition and Premiere Pro).

As usual, Adobe also worked hard on improving the overall performance of its applications. GPU rendering in Premiere can significantly cut down export times, for example, and mask tracking is now up to 38 times faster for 8K videos (and up to 4x faster for HD scenes).

Video is experiencing a golden age as video professionals across broadcast, film, streaming services and digital marketing are facing higher consumer demand for content creation. Meanwhile, production timelines are shorter and the list of deliverables are longer,” said Steven Warner, vice president of Digital Video and Audio at Adobe. “Through optimized performance and intelligent new features powered by Adobe Sensei, video professionals can cut out more tedious production tasks to focus on their creative vision.”

And here’s a bonus for Twitch streamers: they can now use Character Animator to create real-time animation, similar to many of the live animations you may have seen on the Colbert Show (which uses this tool).

Source link




Related posts

Professor Dina Katabi wins Association for Computing Machinery Prize in Computing

Newsemia

Why Artificial Intelligence Will Save Cybersecurity? – CIOL

Newsemia

Dawn Fitzgerald of Schneider Electric to Speak on Preparing the Data Center for AI Ops at AI World Conference & Expo

Newsemia

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy