BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

08/01/2021
by   Bowen Wen, et al.
18

Tracking the 6D pose of objects in video sequences is important for robot manipulation. Most prior efforts, however, often assume that the target object's CAD model, at least at a category-level, is available for offline training or during online template matching. This work proposes BundleTrack, a general framework for 6D pose tracking of novel objects, which does not depend upon 3D models, either at the instance or category-level. It leverages the complementary attributes of recent advances in deep learning for segmentation and robust feature extraction, as well as memory-augmented pose graph optimization for spatiotemporal consistency. This enables long-term, low-drift tracking under various challenging scenarios, including significant occlusions and object motions. Comprehensive experiments given two public benchmarks demonstrate that the proposed approach significantly outperforms state-of-art, category-level 6D tracking or dynamic SLAM methods. When compared against state-of-art methods that rely on an object instance CAD model, comparable performance is achieved, despite the proposed method's reduced information requirements. An efficient implementation in CUDA provides a real-time performance of 10Hz for the entire framework. Code is available at: https://github.com/wenbowen123/BundleTrack

READ FULL TEXT

page 1

page 3

page 6

page 7

research
03/31/2022

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

We present a method that can recognize new objects and estimate their 3D...
research
05/24/2022

OnePose: One-Shot Object Pose Estimation without CAD Models

We propose a new method named OnePose for object pose estimation. Unlike...
research
05/29/2021

Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

Tracking the 6D pose of objects in video sequences is important for robo...
research
07/27/2020

se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

Tracking the 6D pose of objects in video sequences is important for robo...
research
01/10/2023

ROBUSfT: Robust Real-Time Shape-from-Template, a C++ Library

Tracking the 3D shape of a deforming object using only monocular 2D visi...
research
03/24/2023

GarmentTracking: Category-Level Garment Pose Tracking

Garments are important to humans. A visual system that can estimate and ...
research
05/12/2019

Integrating Objects into Monocular SLAM: Line Based Category Specific Models

We propose a novel Line based parameterization for category specific CAD...

Please sign up or login with your details

Forgot password? Click here to reset