UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References
This repository will contain the official implementation of UA-Pose, an uncertainty-aware approach for 6D object pose estimation and online object completion specifically designed for partial references. The source codes will be released soon.
Pipeline of UA-Pose: We assume access to either (1) a limited set of RGBD images with known poses or (2) a single 2D image. For the first case, we initialize a partial object 3D model based on the provided images and poses, while for the second, we use image-to-3D techniques to generate an initial object 3D model. Our method integrates uncertainty into the incomplete 3D model, distinguishing between seen and unseen regions. This uncertainty enables confidence assessment in pose estimation and guides an uncertainty-aware sampling strategy for online object completion, enhancing robustness in pose estimation accuracy and improving object completeness.
Thanks to the following projects for providing their open-source codebases and models.