Carnegie Mellon University Robotics Institute转发了
Excited to present our new work on using diffusion priors for video amodal segmentation and content completion! with Deva Ramanan and Tarasha Khurana. arXiv: https://lnkd.in/e5UDFW8s project page: https://lnkd.in/eMGAGxhi
MS in Computer Vision @ CMU
2 个月Given a modal (visible) object sequence in a video, we develop a two-stage method that generates its amodal (visible + invisible) masks and RGB content. Here, we show one such example of an unseen deformable object category 'laptop' that undergoes a complete occlusion.