Segment humans in image after self-supervised training on multiple views
Segment humans in image after self-supervised training on multiple views
Self-supervised Human Detection and Segmentation via Multi-view Consensus
arXiv paper abstract https://arxiv.org/abs/2012.05119
arXiv PDF paper https://arxiv.org/pdf/2012.05119.pdf
Self-supervised detection and segmentation of foreground objects in complex scenes is gaining attention as their fully-supervised counterparts require overly large amounts of annotated data to deliver sufficient accuracy in domain-specific applications.
However, existing self-supervised approaches predominantly rely on restrictive assumptions on appearance and motion, which precludes their use in scenes depicting highly dynamic activities or involve camera motion.
… propose using a multi-camera framework in which geometric constraints are embedded in the form of multi-view consistency during training
… learn a joint distribution of proposals over multiple views.
At inference time, our method operates on single RGB images.
… approach outperforms state-of-the-art self-supervised person detection and segmentation techniques on images that visually depart from those of standard benchmarks, as well as on those of the classical Human3.6M dataset.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
