cs.CVNov 16, 2026

Exploring the link between predictive uncertainty and the sim-to-real gap in deep learning models utilizing synthetic data

Authors: Alexander Moriz, Lukas Krebs, Amon Göppert, Robert H. Schmitt

Organizations: Chair for Intelligence in Quality Sensing (IQS), WZL | RWTH Aachen University, Campus Boulevard 30, 52074 Aachen, Germany · Fraunhofer Institute for Production Technology IPT, Steinbachstrasse 17, 52074 Aachen, Germany

Abstract

Today, state-of-the-art methods for quality control (QC) are based on Machine Vision, combining deep learning (DL) models with camera-based inspection. Yet, the integration of such solutions in industrial applications is often impeded by data sparsity and trust in model reliability. While synthetic data offers a promising approach to generate the necessary data with perfect annotations, it poses risks related to performance degradation due to the possible occurrence of the sim-to-real gap. This study conducts experiments using the ensemble method to estimate the predictive uncertainty of DL models trained on synthetic data. The results show that predictive uncertainty increases under the sim-to-real domain shift. However, the observed performance drop is dominated by a systematic sim-to-real bias rather than by ensemble disagreement.These findings contribute to the effective utilization of synthetic data in industrial settings while highlighting the importance of risk assessment for the deployment of DL solutions for QC tasks.

Figures & tables

Explore similar work

CardsList
  1. Should I Use This Synthetic Dataset for Training? How to Test with Minimal Real Data

    Aug 28, 2026Zhenyu Tao, Wei Xu, Xiaohu You +2Synthetic Data EvaluationSequential Hypothesis Testing

  2. Towards Intrinsically Calibrated Uncertainty Quantification in Industrial Data-Driven Models via Diffusion Sampler

    Apr 2, 2026Yiran Ma, Jerome Le Ny, Zhichao Chen +1Uncertainty QuantificationUncertainty Calibration

  3. 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