Part of International Conference on Representation Learning 2025 (ICLR 2025) Conference
Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari, Andrea Tagliasacchi, Ghassan Hamarneh, Ali Mahdavi Amiri
Segmenting an object in a video presents significant challenges. Each pixel must be accurately labeled, 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 apre-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. The project page is available at https://segment-me-in-time.github.io/