Get object orientation without training and without 3D model with PIZZA
Get object orientation without training and without 3D model with PIZZA
PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking
arXiv paper abstract https://arxiv.org/abs/2209.07589v1
arXiv PDF paper https://arxiv.org/pdf/2209.07589v1.pdf
Estimating the relative pose of a new object without prior knowledge is a hard problem, while it is an ability very much needed in robotics and Augmented Reality.
… present a method for tracking the 6D motion of objects in RGB video sequences when neither the training images nor the 3D geometry of the objects are available.
… can therefore consider unknown objects in open world instantly, without requiring any prior information or a specific training phase.
… consider two architectures, one based on two frames, and the other relying on a Transformer Encoder, which can exploit an arbitrary number of past frames.
… train … architectures using only synthetic renderings with domain randomization.
… results on challenging datasets are on par with previous works that require much more information (training images of the target objects, 3D models, and/or depth data) …
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
