mlsanityData to 7 Oct 2026

Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

arXiv 1810.10093 ↗First posted 23 Oct 2018cs.CVcited by 94

Not on the map. Why?

Abstract (arXiv)

We present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure and context of the scene. In contrast to DR, which places objects and distractors randomly according to a uniform probability distribution, SDR places objects and distractors randomly according to probability distributions that arise from the specific problem at hand. In this manner, SDR-generated imagery enables the neural network to take the context around an object into consideration during detection. We demonstrate the power of SDR for the problem of 2D bounding box car detection, achieving competitive results on real data after training only on synthetic data. On the KITTI easy, moderate, and hard tasks, we show that SDR outperforms other approaches to generating synthetic data (VKITTI, Sim 200k, or DR), as well as real data collected in a different domain (BDD100K). Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 19; 2023: 24; 2024: 16; 2025: 11; 2026: 3.

94 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  2. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  3. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 195
  4. 2022Parameter-free Online Test-time Adaptationcited by 184
  5. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  6. 2024ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehiclescited by 92
  7. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  8. 2023Language Conditioned Traffic Generationcited by 86
  9. 2021SceneGen: Learning to Generate Realistic Traffic Scenescited by 83
  10. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  11. 2022MIME: Human-Aware 3D Scene Generationcited by 57
  12. 2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 49
38 more
  1. 2023Synthetic Datasets for Autonomous Driving: A Surveycited by 48
  2. 2023All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenescited by 40
  3. 2024Solving Motion Planning Tasks with a Scalable Generative Modelcited by 40
  4. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  5. 2022Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoningcited by 33
  6. 2022TTTFlow: Unsupervised Test-Time Training with Normalizing Flowcited by 33
  7. 2024Mixed Diffusion for 3D Indoor Scene Synthesiscited by 30
  8. 2022Attention Diversification for Domain Generalizationcited by 29
  9. 2021Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Datacited by 26
  10. 2021NViSII: A Scriptable Tool for Photorealistic Image Generationcited by 24
  11. 2021Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehiclescited by 22
  12. 2023ClusT3: Information Invariant Test-Time Trainingcited by 21
  13. 2021CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generationcited by 20
  14. 2023SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervisioncited by 20
  15. 2023SurvivalGAN: Generating Time-to-Event Data for Survival Analysiscited by 17
  16. 2021Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehiclescited by 16
  17. 2023CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embeddingcited by 16
  18. 2022PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Datacited by 14
  19. 2023Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protectioncited by 14
  20. 2021Towards Optimal Strategies for Training Self-Driving Perception Models in Simulationcited by 12
  21. 2021PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Visioncited by 11
  22. 2022Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learningcited by 11
  23. 2023A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptationcited by 11
  24. 2023Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweightingcited by 9
  25. 2025Enhancing Autonomous Driving Safety with Collision Scenario Integrationcited by 9
  26. 2022SimVQA: Exploring Simulated Environments for Visual Question Answeringcited by 8
  27. 2023Aggregation of Disentanglement: Reconsidering Domain Variations in Domain Generalizationcited by 8
  28. 2023Quantifying the LiDAR Sim-to-Real Domain Shift: A Detailed Investigation Using Object Detectors and Analyzing Point Clouds at Target-Levelcited by 7
  29. 2024Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wildcited by 7
  30. 2024Towards Sim-to-Real Industrial Parts Classification with Synthetic Datasetcited by 7
  31. 2024Say No to Freeloader: Protecting Intellectual Property of Your Deep Modelcited by 7
  32. 2024Improving Object Detector Training on Synthetic Data by Starting With a Strong Baseline Methodologycited by 6
  33. 2024Bridging the Domain Gap for Flight-Ready Spaceborne Visioncited by 6
  34. 2025Domain Randomization for Object Detection in Manufacturing Applications using Synthetic Data: A Comprehensive Studycited by 6
  35. 2021Synthetic training data generation for deep learning based quality inspectioncited by 5
  36. 2022Photo-realistic Neural Domain Randomizationcited by 5
  37. 2023Learning Human Action Recognition Representations Without Real Humanscited by 5
  38. 2024Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detectioncited by 5

50 most cited of 94 All 94 (JSON)