PixTrack: Precise 6DoF Object Pose Tracking using NeRF Templates and Feature-metric Alignment
This work addresses object pose tracking for robotics and AR/VR applications, presenting a novel method that improves accuracy and efficiency.
The paper tackles the problem of 6DoF object pose tracking in monocular RGB and RGB-D images by proposing PixTrack, which uses Neural Radiance Fields for novel view synthesis and deep feature-metric alignment, achieving highly accurate, robust, and jitter-free pose estimates without data annotation or trajectory smoothing.
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