Synthetic-to-Real Domain Adaptation

Ask about this topic

Overview

The field studies how to make models trained on simulated or generated data work reliably on real images, sensor readings, and physical systems, where labels may be scarce or costly. Common approaches include physics-based simulation and domain randomization, style translation, feature alignment with adversarial learning or pseudo-labels, and self-supervised or test-time adaptation. Researchers evaluate transfer in settings such as GTA-to-Cityscapes driving, LiDAR perception, robotic manipulation, and medical imaging, often comparing synthetic-only training with mixtures that include real data. A central tension is that visual realism alone may not capture the real domain’s diversity: synthetic data can provide useful supervision, but small amounts of well-matched real data and task-specific adaptation often determine whether gains transfer.

Latest papers

CardsList

137 papers14 papers in the last four weeks, down 33% on the four weeks before. 0.1% of all new papers.

  1. VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution

    Mar 24, 2026August Leander Høeg, Sophia Wiinberg Bardenfleth, Hans Martin Kjer +3Image Super-ResolutionMedical Image Super-Resolution

    Technical University of Denmark, Kgs. Lyngby, Denmark

  2. RAFL: Generalizable Sim-to-Real of Soft Robots with Residual Acceleration Field Learning

    Mar 23, 2026Dong Heon Cho, Boyuan ChenSynthetic-to-Real Domain AdaptationResidual Dynamics Learning

    Department of Computer Science, Duke University, 308 Research Dr., Durham, 27705, NC, USA · Department of Mechanical Engineering and Material Science, 121 Hudson Hall, Durham, 27708, NC, USA · Department of Electrical and Computer Engineering, 100 Science Dr., Durham, 27708, NC, USA

  3. Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis

    Mar 23, 2026Kangbo Zhao, Miaoxin Guan, Xiang Chen +2Image DerainingSynthetic-to-Real Domain Adaptation

    School of Information Engineering, Guangdong University of Technology, Guangzhou, 510006, China · School of Computer Science and Engineering, Nanjing University of Science and Technology

  4. From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Driving

    Mar 18, 2026A. Humnabadkar, A. Sikdar, B. Cave +3Autonomous DrivingAutonomous Driving Simulation

    Department of Computer Science, Edge Hill University, United Kingdom.

  5. Structured prototype regularization for synthetic-to-real driving scene parsing

    Mar 17, 2026Jiahe Fan, Xiao Ma, Sergey Vityazev +3Synthetic-to-Real Domain AdaptationUnsupervised Domain Adaptation

    Tongji University, Shanghai 201804, China · Beijing Institute of Aerospace Control Devices, Beijing 100039, China · Ryazan State Radio Engineering University, Ryazan 390005, Russia +1

  6. Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation

    Mar 11, 2026Natsuo Yamashita, Koichi Nagatsuka, Hiroaki Kokubo +2Large Language Model-Based Data AugmentationDomain Adaptation for ASR

    Hitachi, Ltd.

  7. Real-Time Monocular Scene Analysis for UAV in Outdoor Environments

    Mar 9, 2026Yara AlaaEldinMonocular Depth EstimationSynthetic-to-Real Domain Adaptation

    University of Genova; DRIM; Ph.D. Program of National Interest in Robotics and Intelligent Machines; Administrative Headquarters: Università di Genova

  8. Bi-directional digital twin prototype anchoring with multi-periodicity learning for few-shot fault diagnosis

    Mar 7, 2026Pengcheng Xia, Zhichao Dong, Yixiang Huang +3Fault DiagnosisIndustrial Fault Diagnosis

    State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, PR China

  9. Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy

    Mar 5, 2026Peter Lalor, Ayush Panigrahy, Alex HagenSynthetic-to-Real Domain AdaptationUnsupervised Domain Adaptation

    Pacific Northwest National Laboratory, Richland, WA 99352 USA · University of Washington, Seattle, WA 98195 USA

  10. Engineering Regression Without Real-Data Training: Domain Adaptation for Tabular Foundation Models Using Multi-Dataset Embeddings

    Mar 5, 2026Lyle Regenwetter, Rosen Yu, Cyril Picard +1Synthetic Data PretrainingSynthetic-to-Real Domain Adaptation

    Massachusetts Institute of Technology

  11. Self-supervised Domain Adaptation for Visual 3D Pose Estimation of Nano-drone Racing Gates by Enforcing Geometric Consistency

    Mar 3, 2026Nicholas Carlotti, Michele Antonazzi, Elia Cereda +4Relative Pose EstimationObject Pose Estimation

    Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland · University of Milan, Italy · Integrated Systems Laboratory (IIS), ETHZ, Zürich, Switzerland

  12. Single Microphone Own Voice Detection based on Simulated Transfer Functions for Hearing Aids

    Mar 3, 2026Mathuranathan Mayuravaani, W. Bastiaan Kleijn, Andrew Lensen +1Synthetic-to-Real Domain AdaptationSynthetic Data Augmentation

  13. Structure-to-Image: Zero-Shot Depth Estimation in Colonoscopy via High-Fidelity Sim-to-Real Adaptation

    Feb 25, 2026Juan Yang, Yuyan Zhang, Han Jia +2Monocular Depth EstimationSynthetic-to-Real Domain Adaptation

    College of Computer Science, Sichuan University, Chengdu, China · Department of Gastroenterology and Hepatology, West China Hospital, Sichuan University, Chengdu, China

  14. SynthRender and I-AsSET: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception

    Feb 24, 2026Jose Moises Araya-Martinez, Thushar Tom, Adrián Sanchis Reig +3Sim-to-Real TransferSynthetic-to-Real Domain Adaptation

    Technical University Berlin, Industrial Automation Technology, Berlin, Germany · Mercedes-Benz AG, Future Manufacturing Technologies, Sindelfingen, Germany · Technical University Braunschweig, Institute for Cognitive Robotics, Braunschweig, Germany

  15. When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

    Feb 23, 2026Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov +3Synthetic-to-Real Domain AdaptationDistribution Shift

    1RPTU University Kaiserslautern-Landau, Kaiserslautern, Germany · 2German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany

  16. OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection

    May 26, 2025David Schneider, Zdravko Marinov, Moritz Mistol +6Synthetic-to-Real Domain AdaptationFall Detection

    Karlsruhe Institute of Technology · Mercedes-Benz Tech Innovation

  17. Synthetic Enclosed Echoes: A New Dataset to Mitigate the Gap Between Simulated and Real-World Sonar Data

    May 21, 2025Guilherme de Oliveira, Matheus M. dos Santos, Paulo L. J. Drews-JrSynthetic-to-Real Domain AdaptationUnderwater Imaging

    NAUTEC - Intelligent robotics and automation group, FURG - Federal University of Rio Grande, Rio Grande, RS, Brazil · ICMC - Institute of Mathematics and Computer Sciences, USP - University of S˜ao Paulo, S˜ao Carlos, SP, Brazil