This novel approach can deal with associated objects in a smart way.
Have a look at a new approach that allows users to remove objects and backgrounds from images. The model defines an object and leaves other details associated with this object. For example, users can keep complex effects such as shadows, reflections, smoke, or ripples the subject creates in water.
The research team noted that scene effects related to the objects (shadows, reflections, generated smoke, etc) are usually overlooked by similar methods.
"Identifying such scene effects and associating them with the objects producing them is important for improving our fundamental understanding of visual scenes, and can also assist a variety of applications such as removing, duplicating, or enhancing objects in video." notes the abstract. "In this work, we take a step towards solving this novel problem of automatically associating objects with their effects in a video. Given an ordinary video and a rough segmentation mask over time of one or more subjects of interest, we estimate an omnimatte for each subject – an alpha matte and color image that includes the subject along with all its related time-varying scene elements."
Learn more about the approach here. Don't forget to join our new Telegram channel, our Discord, follow us on Instagram and Twitter, where we are sharing breakdowns, the latest news, awesome artworks, and more.