Get object pose from only a few images and using an arbitrary object detector with Cas6D
Get object pose from only a few images and using an arbitrary object detector with Cas6D
Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images
arXiv paper abstract https://arxiv.org/abs/2306.07598
arXiv PDF paper https://arxiv.org/pdf/2306.07598.pdf
The accurate estimation of six degrees-of-freedom (6DoF) object poses is essential for many applications in robotics and augmented reality.
… present a new cascade framework named Cas6D for few-shot 6DoF pose estimation that is generalizable and uses only RGB images.
To address the false positives of target object detection in the extreme few-shot setting, … framework utilizes a selfsupervised pre-trained ViT to learn robust feature representations.
… initialize the nearest top-K pose candidates based on similarity score and refine the initial poses using feature pyramids to formulate and update the cascade warped feature volume, which encodes context at increasingly finer scales.
By discretizing the pose search range using multiple pose bins and progressively narrowing the pose search range in each stage using predictions from the previous stage, Cas6D can overcome the large gap between pose candidates and ground truth poses
… Cas6D outperforms state-of-the-art methods by 9.2% and 3.8% accuracy (Proj-5) under the 32-shot setting compared to OnePose++ and Gen6D.
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
