Home > Research > Publications & Outputs > Leveraging Synthetic Data to Learn Video Stabil...

Research

Associated organisational units

Electronic data

Keywords

View graph of relations

Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Forthcoming

Standard

Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions. / Kerim, Abdulrahman; De Souza Ramos, Washington; Soriano Marcolino, Leandro et al.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2023.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Kerim, A, De Souza Ramos, W, Soriano Marcolino, L, Nascimento, ER & Jiang, R 2023, Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions. in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), United States, 4/01/24.

APA

Kerim, A., De Souza Ramos, W., Soriano Marcolino, L., Nascimento, E. R., & Jiang, R. (in press). Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions. In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Vancouver

Kerim A, De Souza Ramos W, Soriano Marcolino L, Nascimento ER, Jiang R. Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions. In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2023

Author

Kerim, Abdulrahman ; De Souza Ramos, Washington ; Soriano Marcolino, Leandro et al. / Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2023.

Bibtex

@inproceedings{f41a9ff48ccd437ca26dd1298964acd5,
title = "Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions",
abstract = "Stabilization plays a central role in improving the quality of videos. However, current methods perform poorly under adverse conditions. In this paper, we propose a synthetic-aware adverse weather video stabilization algorithm that dispenses real data for training, relying solely on synthetic data. Our approach leverages specially generated synthetic data to avoid the feature extraction issues faced by current methods. To achieve this, we present a novel data generator to produce the required training data with an automatic ground-truth extraction procedure. We also propose a new dataset, VSAC105Real, and compare our method to five recent video stabilization algorithms using two benchmarks. Our method generalizes well on real-world videos across all weather conditions and does not require large-scale synthetic training data. Implementations for our proposed video stabilization algorithm, generator, and datasets are available at https://github.com/A-Kerim/SyntheticData4VideoStabilization_WACV_2024.",
keywords = "Synthetic Data, Computer Vision, Video Stabilization",
author = "Abdulrahman Kerim and {De Souza Ramos}, Washington and {Soriano Marcolino}, Leandro and Nascimento, {Erickson R.} and Richard Jiang",
year = "2023",
month = oct,
day = "24",
language = "English",
booktitle = "IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)",
note = "IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), WACV ; Conference date: 04-01-2024 Through 08-01-2024",
url = "https://wacv2024.thecvf.com/",

}

RIS

TY - GEN

T1 - Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions

AU - Kerim, Abdulrahman

AU - De Souza Ramos, Washington

AU - Soriano Marcolino, Leandro

AU - Nascimento, Erickson R.

AU - Jiang, Richard

PY - 2023/10/24

Y1 - 2023/10/24

N2 - Stabilization plays a central role in improving the quality of videos. However, current methods perform poorly under adverse conditions. In this paper, we propose a synthetic-aware adverse weather video stabilization algorithm that dispenses real data for training, relying solely on synthetic data. Our approach leverages specially generated synthetic data to avoid the feature extraction issues faced by current methods. To achieve this, we present a novel data generator to produce the required training data with an automatic ground-truth extraction procedure. We also propose a new dataset, VSAC105Real, and compare our method to five recent video stabilization algorithms using two benchmarks. Our method generalizes well on real-world videos across all weather conditions and does not require large-scale synthetic training data. Implementations for our proposed video stabilization algorithm, generator, and datasets are available at https://github.com/A-Kerim/SyntheticData4VideoStabilization_WACV_2024.

AB - Stabilization plays a central role in improving the quality of videos. However, current methods perform poorly under adverse conditions. In this paper, we propose a synthetic-aware adverse weather video stabilization algorithm that dispenses real data for training, relying solely on synthetic data. Our approach leverages specially generated synthetic data to avoid the feature extraction issues faced by current methods. To achieve this, we present a novel data generator to produce the required training data with an automatic ground-truth extraction procedure. We also propose a new dataset, VSAC105Real, and compare our method to five recent video stabilization algorithms using two benchmarks. Our method generalizes well on real-world videos across all weather conditions and does not require large-scale synthetic training data. Implementations for our proposed video stabilization algorithm, generator, and datasets are available at https://github.com/A-Kerim/SyntheticData4VideoStabilization_WACV_2024.

KW - Synthetic Data

KW - Computer Vision

KW - Video Stabilization

M3 - Conference contribution/Paper

BT - IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

T2 - IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Y2 - 4 January 2024 through 8 January 2024

ER -