Real-time video object segmentation by using global assignment and semantic features with TCOVIS
Real-time video object segmentation by using global assignment and semantic features with TCOVIS
TCOVIS: Temporally Consistent Online Video Instance Segmentation
arXiv paper https://arxiv.org/abs/2309.11857
arXiv PDF paper https://arxiv.org/pdf/2309.11857.pdf
... progress has been made in video instance segmentation (VIS), with many offline and online methods achieving state-of-the-art performance ... online methods are more practical, but maintaining temporal consistency remains a challenging task.
... propose a novel online method for video instance segmentation, called TCOVIS, which fully exploits the temporal information in a video clip.
... method consists of a global instance assignment strategy and a spatio-temporal enhancement module, which improve the temporal consistency of the features from two aspects.
... perform global optimal matching between the predictions and ground truth across the whole video clip, and supervise the model with the global optimal objective.
... also capture the spatial feature and aggregate it with the semantic feature between frames, thus realizing the spatio-temporal enhancement.
... achieve state-of-the-art performance on all benchmarks without bells-and-whistles.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments