Benchmarking Domain Randomisation for Visual Sim-to-Real Transfer
Not on the map. Why?
Abstract (arXiv)
Domain randomisation is a very popular method for visual sim-to-real transfer in robotics, due to its simplicity and ability to achieve transfer without any real-world images at all. Nonetheless, a number of design choices must be made to achieve optimal transfer. In this paper, we perform a comprehensive benchmarking study on these different choices, with two key experiments evaluated on a real-world object pose estimation task. First, we study the rendering quality, and find that a small number of high-quality images is superior to a large number of low-quality images. Second, we study the type of randomisation, and find that both distractors and textures are important for generalisation to novel environments.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Nov 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 2; 2023: 2; 2024: 5; 2025: 1; 2026: 1.
15 papers.
Sort:
By area:
- 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
- 2021SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereocited by 18
- 2024Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulationcited by 11
- 2021Coarse-to-Fine for Sim-to-Real: Sub-Millimetre Precision Across Wide Task Spacescited by 9
- 2022Sim2Real Instance-Level Style Transfer for 6D Pose Estimationcited by 9
- 2021Learning Eye-in-Hand Camera Calibration from a Single Imagecited by 8
- 2024ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimationcited by 6
- 2022Photo-realistic Neural Domain Randomizationcited by 5
- 2023Robust Visual Sim-to-Real Transfer for Robotic Manipulationcited by 5
- 2024Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adaptationcited by 4
- 2023Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learningcited by 2
- 2024Drone Detection using Deep Neural Networks Trained on Pure Synthetic Datacited by 1
3 more
- 2025The Emergence of Deep Reinforcement Learning for Path Planningcited by 1
- 2024Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detectioncited by 0
- 2026InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policiescited by 0
- 2026InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies23 Sep 2026
- 2025The Emergence of Deep Reinforcement Learning for Path Planning21 Jul 2025
- 2024Drone Detection using Deep Neural Networks Trained on Pure Synthetic Data13 Nov 2024
- 2024Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation10 Jul 2024
- 2024ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimation25 Mar 2024
- 2024Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adaptation18 Mar 2024
- 2024Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection6 Mar 2024
- 2023Robust Visual Sim-to-Real Transfer for Robotic Manipulation28 Jul 2023
- 2023Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning28 Jan 2023
- 2022Photo-realistic Neural Domain Randomization23 Oct 2022
- 2022Sim2Real Instance-Level Style Transfer for 6D Pose Estimation3 Mar 2022
- 2021Learning Eye-in-Hand Camera Calibration from a Single Image1 Nov 2021
- 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
- 2021SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereocited by 18
- 2024Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulationcited by 11
- 2021Coarse-to-Fine for Sim-to-Real: Sub-Millimetre Precision Across Wide Task Spacescited by 9
- 2022Sim2Real Instance-Level Style Transfer for 6D Pose Estimationcited by 9
- 2021Learning Eye-in-Hand Camera Calibration from a Single Imagecited by 8
- 2024ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimationcited by 6
- 2022Photo-realistic Neural Domain Randomizationcited by 5
- 2023Robust Visual Sim-to-Real Transfer for Robotic Manipulationcited by 5
- 2024Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adaptationcited by 4
- 2023Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learningcited by 2
- 2024Drone Detection using Deep Neural Networks Trained on Pure Synthetic Datacited by 1
12 most cited of 14 All 14 (JSON)
- 2025The Emergence of Deep Reinforcement Learning for Path Planning21 Jul 2025
- 2024Drone Detection using Deep Neural Networks Trained on Pure Synthetic Data13 Nov 2024
- 2024Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation10 Jul 2024
- 2024ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimation25 Mar 2024
- 2024Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adaptation18 Mar 2024
- 2024Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection6 Mar 2024
- 2023Robust Visual Sim-to-Real Transfer for Robotic Manipulation28 Jul 2023
- 2023Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning28 Jan 2023
- 2022Photo-realistic Neural Domain Randomization23 Oct 2022
- 2022Sim2Real Instance-Level Style Transfer for 6D Pose Estimation3 Mar 2022
- 2021Learning Eye-in-Hand Camera Calibration from a Single Image1 Nov 2021
- 2021Robot Learning from Randomized Simulations: A Review1 Nov 2021
12 newest of 14 All 14 (JSON)