Augmenting Anomaly Detection Datasets with Relighting and Depth Estimation
Year: 2025
Type: dataset
Abstract: Variations in lighting from weather, day–night cycles, seasonal changes, or artificial sources can cause data drift in deep learning models by altering scene appearance, which leads to degraded performance. This is particularly problematic for outdoor anomaly detection, where training and testing datasets are usually limited to daytime recordings. In this paper, we present initial research on using an image relighting model with depth estimation to build augmented surrogate models of datasets under diverse lighting conditions. We show that such datasets pose significant challenges for anomaly detectors and can enable the development of more robust models. Furthermore, these surrogate relit datasets can support a wide range of outdoor vision tasks.
Author: Nikolov, Ivan Adriyanov; id_orcid 0000-0002-4952-8848
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7112045780
Cites:
Cited by:
Related to: