mlsanityData to 7 Oct 2026

ParaPose: Parameter and Domain Randomization Optimization for Pose Estimation using Synthetic Data

arXiv 2203.00945 ↗First posted 2 Mar 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Pose estimation is the task of determining the 6D position of an object in a scene. Pose estimation aid the abilities and flexibility of robotic set-ups. However, the system must be configured towards the use case to perform adequately. This configuration is time-consuming and limits the usability of pose estimation and, thereby, robotic systems. Deep learning is a method to overcome this configuration procedure by learning parameters directly from the dataset. However, obtaining this training data can also be very time-consuming. The use of synthetic training data avoids this data collection problem, but a configuration of the training procedure is necessary to overcome the domain gap problem. Additionally, the pose estimation parameters also need to be configured. This configuration is jokingly known as grad student descent as parameters are manually adjusted until satisfactory results are obtained. This paper presents a method for automatic configuration using only synthetic data. This is accomplished by learning the domain randomization during network training, and then using the domain randomization to optimize the pose estimation parameters. The developed approach shows state-of-the-art performance of 82.0 % recall on the challenging OCCLUSION dataset, outperforming all previous methods with a large margin. These results prove the validity of automatic set-up of pose estimation using purely synthetic data.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

22 of 38 references.

References · 22

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017Mask R-CNNcited by 7,259
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  7. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  8. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  9. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  10. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  11. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  12. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
10 more
  1. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  2. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  3. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  4. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  5. 2020PointMixup: Augmentation for Point Cloudscited by 104
  6. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  7. 2020PointAugment: an Auto-Augmentation Framework for Point Cloud Classificationcited by 65
  8. 2019HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learningcited by 13
  9. 2019PointVoteNet: Accurate Object Detection and 6 DoF Pose Estimation in Point Cloudscited by 7
  10. 2019PDA: Progressive Data Augmentation for General Robustness of Deep Neural Networkscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 1.

5 papers.

  1. 2023KeyMatchNet: Zero-Shot Pose Estimation in 3D Point Clouds by Generalized Keypoint Matchingcited by 7
  2. 2022In-Hand Pose Estimation and Pin Inspection for Insertion of Through-Hole Componentscited by 3
  3. 2023Off-the-shelf bin picking workcell with visual pose estimation: A case study on the world robot summit 2018 kitting taskcited by 3
  4. 2023Facilitating Sim-to-real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulationcited by 2
  5. 2024Good Grasps Only: A data engine for self-supervised fine-tuning of pose estimation using grasp poses for verificationcited by 2