Get object pose with self-supervised learning on videos with self-pose

Get object pose with self-supervised learning on videos with self-pose

Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild

arXiv paper abstract https://arxiv.org/abs/2210.07199

arXiv PDF paper https://arxiv.org/pdf/2210.07199.pdf

Twitter video https://twitter.com/xiaolonw/status/1580767003903606784

Project page https://kywind.github.io/self-pose

While 6D object pose estimation has wide applications across computer vision and robotics, it remains far from being solved due to the lack of annotations.

... problem ... even more challenging when moving to category-level 6D pose, which requires generalization to unseen instances.

... overcome this barrier by introducing a self-supervised learning approach trained directly on large-scale real-world object videos for category-level 6D pose estimation in the wild.

... framework reconstructs the canonical 3D shape of an object category and learns dense correspondences between input images and the canonical shape via surface embedding.

For training, ... propose novel geometrical cycle-consistency losses which construct cycles across 2D-3D spaces, across different instances and different time steps.

... method, without any human annotations or simulators, can achieve on-par or even better performance than previous supervised or semi-supervised methods on in-the-wild images ...

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 LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b #ComputerVision #3D #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning