An Illumination-Robust Feature Extractor Augmented by Relightable 3D Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909331511836672 |
|---|---|
| author | Zhao, Shunyi Yu, Zehuan Fan, Zuxin Zhou, Zhihao Ruan, Lecheng Wang, Qining |
| author_facet | Zhao, Shunyi Yu, Zehuan Fan, Zuxin Zhou, Zhihao Ruan, Lecheng Wang, Qining |
| contents | Visual features, whose description often relies on the local intensity and gradient direction, have found wide applications in robot navigation and localization in recent years. However, the extraction of visual features is usually disturbed by the variation of illumination conditions, making it challenging for real-world applications. Previous works have addressed this issue by establishing datasets with variations in illumination conditions, but can be costly and time-consuming. This paper proposes a design procedure for an illumination-robust feature extractor, where the recently developed relightable 3D reconstruction techniques are adopted for rapid and direct data generation with varying illumination conditions. A self-supervised framework is proposed for extracting features with advantages in repeatability for key points and similarity for descriptors across good and bad illumination conditions. Experiments are conducted to demonstrate the effectiveness of the proposed method for robust feature extraction. Ablation studies also indicate the effectiveness of the self-supervised framework design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_00629 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Illumination-Robust Feature Extractor Augmented by Relightable 3D Reconstruction Zhao, Shunyi Yu, Zehuan Fan, Zuxin Zhou, Zhihao Ruan, Lecheng Wang, Qining Computer Vision and Pattern Recognition Visual features, whose description often relies on the local intensity and gradient direction, have found wide applications in robot navigation and localization in recent years. However, the extraction of visual features is usually disturbed by the variation of illumination conditions, making it challenging for real-world applications. Previous works have addressed this issue by establishing datasets with variations in illumination conditions, but can be costly and time-consuming. This paper proposes a design procedure for an illumination-robust feature extractor, where the recently developed relightable 3D reconstruction techniques are adopted for rapid and direct data generation with varying illumination conditions. A self-supervised framework is proposed for extracting features with advantages in repeatability for key points and similarity for descriptors across good and bad illumination conditions. Experiments are conducted to demonstrate the effectiveness of the proposed method for robust feature extraction. Ablation studies also indicate the effectiveness of the self-supervised framework design. |
| title | An Illumination-Robust Feature Extractor Augmented by Relightable 3D Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.00629 |