@inproceedings{scholars17464,
             doi = {10.1109/ROMA55875.2022.9915679},
            year = {2022},
            note = {cited By 0; Conference of 5th IEEE International Symposium in Robotics and Manufacturing Automation, ROMA 2022 ; Conference Date: 6 August 0202 Through 8 August 0202; Conference Code:183507},
           title = {Synthetic to Real Gap Estimation of Autonomous Driving Datasets using Feature Embedding},
         journal = {2022 IEEE 5th International Symposium in Robotics and Manufacturing Automation, ROMA 2022},
       publisher = {Institute of Electrical and Electronics Engineers Inc.},
            isbn = {9781665459327},
          author = {Gadipudi, N. and Elamvazuthi, I. and Sanmugam, M. and Izhar, L. I. and Prasetyo, T. and Jegadeeshwaran, R. and Ali, S. S. A.},
        abstract = {Recent advances in autonomous driving using deep learning have drawn immense attention from robotics and computer vision communities. Training generalized deep learning models for autonomous driving tasks like visual odometry, segmentation, and object detection requires large amounts of data. Acquiring real-world data with accurate annotations is time-consuming and expensive. Due to this challenge, synthetic datasets are increasingly being used for training and testing deep learning models. Synthetic data lacks the appearance and contextual properties of real-world datasets. Several works have been shown to reduce this gap between synthetic and real-world images. However, evaluating the gap between the synthetic and real-world datasets is a longstanding challenge because of its highly not deterministic nature. This research proposes the use of feature embedding techniques to address this synthetic to reality gap in the form of distance between different data clusters. From the experiments, the proposed approach estimated the distance between real-world to enhanced virtual datasets is 6-10 times the distance between real-world to virtual datasets. {\^A}{\copyright} 2022 IEEE.},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85141550160&doi=10.1109\%2fROMA55875.2022.9915679&partnerID=40&md5=7de11b19e173f076ecdf6323f754d7d0},
        keywords = {Autonomous vehicles; Computer vision; Deep learning; Embeddings, Autonomous driving; Driving tasks; Feature embedding; Learning models; Real-world; Real-world datasets; Reality gaps; Synthetic datasets; Vision communities; Visual segmentation, Object detection}
}