Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
This addresses the problem of domain shift in pose tracking for robotics, offering a practical solution with synthetic-to-real transfer, though it is incremental in improving existing methods.
The paper tackles 6D pose tracking for robot manipulation by introducing se(3)-TrackNet, a data-driven optimization method that uses synthetic data training to achieve robust real-time performance at 90.9Hz, outperforming alternatives trained on real images in benchmarks.
Tracking the 6D pose of objects in video sequences is important for robot manipulation. This work presents se(3)-TrackNet, a data-driven optimization approach for long term, 6D pose tracking. It aims to identify the optimal relative pose given the current RGB-D observation and a synthetic image conditioned on the previous best estimate and the object's model. The key contribution in this context is a novel neural network architecture, which appropriately disentangles the feature encoding to help reduce domain shift, and an effective 3D orientation representation via Lie Algebra. Consequently, even when the network is trained solely with synthetic data can work effectively over real images. Comprehensive experiments over multiple benchmarks show se(3)-TrackNet achieves consistently robust estimates and outperforms alternatives, even though they have been trained with real images. The approach runs in real time at 90.9Hz. Code, data and supplementary video for this project are available at https://github.com/wenbowen123/iros20-6d-pose-tracking