Leveraging synthetic data to learn video stabilization under adverse conditions

Kerim, Abdulrahman and Ramos, Washington and Leandro, Soriano Marcolino and Nascimento, Erickson and Jiang, Richard (2023) Leveraging synthetic data to learn video stabilization under adverse conditions. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 4-8 January 2024, Waikoloa, Hawaii, USA. (In Press)

Documents
Details

[+][-]

Documents

6213:121232
6213:121233

[+][-]

6213:121232

Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions - Kerim, Ramos, Leandro, Nascimento and Jiang (1MB)

6213:121233

Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions -Kerim, Ramos, Leandro, Nascimento and Jiang (218kB)

Details

Creators:

Kerim, Abdulrahman and Ramos, Washington and Leandro, Soriano Marcolino and Nascimento, Erickson and Jiang, Richard

Description/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.

Item Type:

Conference or Workshop Item

Date:

24 October 2023

Funders:

Lancaster University - FST, Lancaster University - High End Computing (HEC)

Event Location:

Waikoloa, Hawaii, USA

Projects or Series:

Synthetic Data for Machine Learning

Schools:

School of Games & Creative Technology