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

arXiv: https://arxiv.org/abs/2105.14391 · HTML: https://mlsanity.com/paper/2105.14391/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 29 May 2021.

## Builds on (most cited first, 18 of 18)

- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [Implicit 3D Orientation Learning for 6D Object Detection from RGB Images](https://mlsanity.com/paper/1902.01275/) (2019)
- [PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking](https://mlsanity.com/paper/1905.09304/) (2019)
- [se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains](https://mlsanity.com/paper/2007.13866/) (2020)
- [Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands](https://mlsanity.com/paper/2003.03518/) (2020)
- [Depth-Based Object Tracking Using a Robust Gaussian Filter](https://mlsanity.com/paper/1602.06157/) (2016)
- [Probabilistic Object Tracking using a Range Camera](https://mlsanity.com/paper/1505.00241/) (2015)
- [A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking](https://mlsanity.com/paper/1807.02087/) (2018)
- [Deep 6-DOF Tracking](https://mlsanity.com/paper/1703.09771/) (2017)
- [Task-driven Perception and Manipulation for Constrained Placement of Unknown Objects](https://mlsanity.com/paper/2006.15503/) (2020)
- [Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects](https://mlsanity.com/paper/1910.04953/) (2019)

## Built on by (most cited first, 5 of 5)

- [You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration](https://mlsanity.com/paper/2201.12716/) (2022)
- [TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation](https://mlsanity.com/paper/2303.16730/) (2023)
- [SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World](https://mlsanity.com/paper/2110.12715/) (2021)
- [Accidental Turntables: Learning 3D Pose by Watching Objects Turn](https://mlsanity.com/paper/2212.06300/) (2022)
- [Few-Shot Object Detection in Unseen Domains](https://mlsanity.com/paper/2204.05072/) (2022)

## Abstract (arXiv)

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