mlsanityData to 7 Oct 2026

Sim2Real Instance-Level Style Transfer for 6D Pose Estimation

arXiv 2203.02069 ↗First posted 3 Mar 2022cs.CV cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

In recent years, synthetic data has been widely used in the training of 6D pose estimation networks, in part because it automatically provides perfect annotation at low cost. However, there are still non-trivial domain gaps, such as differences in textures/materials, between synthetic and real data. These gaps have a measurable impact on performance. To solve this problem, we introduce a simulation to reality (sim2real) instance-level style transfer for 6D pose estimation network training. Our approach transfers the style of target objects individually, from synthetic to real, without human intervention. This improves the quality of synthetic data for training pose estimation networks. We also propose a complete pipeline from data collection to the training of a pose estimation network and conduct extensive evaluation on a real-world robotic platform. Our evaluation shows significant improvement achieved by our method in both pose estimation performance and the realism of images adapted by the style transfer.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

27 of 32 references.

References · 27

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  4. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  6. 2018Which Training Methods for GANs do actually Converge?cited by 672
  7. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  8. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 593
  9. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  10. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  11. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  12. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
15 more
  1. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  2. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  3. 2017Image to Image Translation for Domain Adaptationcited by 171
  4. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  5. 2015Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocolscited by 98
  6. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  7. 2019BlenderProccited by 76
  8. 2021Enhancing Photorealism Enhancementcited by 74
  9. 2019Towards Instance-level Image-to-Image Translationcited by 36
  10. 2020Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglementcited by 15
  11. 2020Benchmarking Domain Randomisation for Visual Sim-to-Real Transfercited by 15
  12. 2021DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistencycited by 14
  13. 2018Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotationscited by 12
  14. 2020Stillleben: Realistic Scene Synthesis for Deep Learning in Roboticscited by 11
  15. 2020Style-transfer GANs for bridging the domain gap in synthetic pose estimator trainingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 2; 2026: 1.

9 papers.

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  2. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  3. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  4. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
  5. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  6. 20226IMPOSE: Bridging the Reality Gap in 6D Pose Estimation for Robotic Graspingcited by 1
  7. 2026Component-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data Constructioncited by 1
  8. 2025SCOPE: Semantic Conditioning for Sim2Real Category-Level Object Pose Estimation in Roboticscited by 0
  9. 2025WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusioncited by 0