We present PixTrack, a vision based object pose tracking framework using novel view synthesis and deep feature-metric alignment. We follow an SfM-based relocalization paradigm where we use a Neural Radiance Field to canonically represent the tracked object. Our evaluations demonstrate that our method produces highly accurate, robust, and jitter-free 6DoF pose estimates of objects in both monocular RGB images and RGB-D images without the need of any data annotation or trajectory smoothing. Our method is also computationally efficient making it easy to have multi-object tracking with no alteration to our algorithm through simple CPU multiprocessing. Our code is available at: https://github.com/GiantAI/pixtrack
@article{arxiv.2209.03910,
title = {PixTrack: Precise 6DoF Object Pose Tracking using NeRF Templates and Feature-metric Alignment},
author = {Prajwal Chidananda and Saurabh Nair and Douglas Lee and Adrian Kaehler},
journal= {arXiv preprint arXiv:2209.03910},
year = {2024}
}