has an artificial intelligence project that lets anyone bring their doodles to life. The company hopes that by offering Animated Drawings as an open-source project other developers will be able to create new, richer experiences.
The Fundamental AI Research (FAIR) team originally released a web-based version of the tool in 2021. It asks users to upload a drawing of a single human-like character or to select a demo figure. If you use your own doodle, you’ll see a consent form that asks if Meta can use your drawing to help train its models. You don’t need to provide consent to keep using the tool.
Next, you’ll need to resize a capture box so it fits snugly around your creation. The tool gives you a pen and eraser to tweak the drawing before adjusting where the joints should be. After all that, you’ll see an animated version of your sketch. You can pick from a variety of preset animations from four categories: dance, funny, jumping and walking.
Animated Drawings harnesses object detection models, pose estimation models and image processing-based segmentation methods to capture a digital version of a drawing. It then uses traditional computer graphics techniques to deform and animate the image.
Within a few months of , users had granted Meta permission to use more than 1.6 million images for training purposes. Some folks uploaded images of company logos, anime characters, fish and stuffed animals, despite the tool stipulating that only human figures would work.
Along with requests for a more in-depth toolset that includes sound effects and text overlays, the array of images that people uploaded to the tool suggested there was broad interest in more extensive drawing-to-animation experiences. That, in part, led to Meta open sourcing the project with a dataset of around 180,000 drawings. “By releasing the models and code as open source, the project provides a starting point for developers to build on and extend the project, fostering a culture of innovation and collaboration within the open source community,” Meta wrote in a blog post.
Source link
