Paper · arXiv 2410.18538
SMITE: Segment Me In TimE
Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari Taghanaki, Andrea Tagliasacchi, Ghassan Hamarneh, Ali Mahdavi Amiri
A pre-trained text-to-image diffusion model with tracking mechanism outperforms existing methods in object segmentation across video frames with arbitrary granularity.
Abstract
Segmenting an object in a video presents significant challenges. Each pixel must be accurately labelled, and these labels must remain consistent across frames. The difficulty increases when the segmentation is with arbitrary granularity, meaning the number of segments can vary arbitrarily, and masks are defined based on only one or a few sample images. In this paper, we address this issue by employing a pre-trained text to image diffusion model supplemented with an additional tracking mechanism. We demonstrate that our approach can effectively manage various segmentation scenarios and outperforms state-of-the-art alternatives.