EUVIMEDEUVIMED entdecken
Crossref

Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond

Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Yihang Luo, Chen Change Loy

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-11 · 46 (11) · 7041-7055

DOI: 10.1109/tpami.2024.3406821 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-11. Verfasst von Yuekun Dai und 5 weiteren Autor:innen. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Industry Alignment Fund Industry Collaborati on Projects, in-kind contribution from the industry partner.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial lights commonly leave strong lens flare artifacts on the images captured at night, degrading both the visual quality and performance of vision algorithms. Existing flare removal approaches mainly focus on removing daytime flares and fail in nighttime cases. Nighttime flare removal is challenging due to the unique luminance and spectrum of artificial lights, as well as the diverse patterns and image degradation of the flares. The scarcity of the nighttime flare removal dataset constrains the research on this crucial task. In this paper, we introduce Flare7K++, the first comprehensive nighttime flare removal dataset, consisting of 962 real-captured flare images (Flare-R) and 7000 synthetic flares (Flare7K). Compared to Flare7K, Flare7K++ is particularly effective in eliminating complicated degradation around the light source, which is intractable by using synthetic flares alone. Besides, the previous flare removal pipeline relies on the manual threshold and blur kernel settings to extract light sources, which may fail when the light sources are tiny or not overexposed. To address this issue, we additionally provide the annotations of light sources in Flare7K++ and propose a new end-to-end pipeline to preserve the light source while removing lens flares. Our dataset and pipeline offer a valuable foundation and benchmark for future investigations into nighttime flare removal studies. Extensive experiments demonstrate that Flare7K++ supplements the diversity of existing flare datasets and pushes the frontier of nighttime flare removal toward real-world scenarios.

Förderung

  • Industry Alignment Fund Industry Collaborati on Projects
  • in-kind contribution from the industry partner

Zitieren

APA

Dai, Y., Li, C., Zhou, S., Feng, R., Luo, Y., & Loy, C. C. (2024). Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(11), 7041-7055. https://doi.org/10.1109/tpami.2024.3406821

Vancouver

Dai Y, Li C, Zhou S, Feng R, Luo Y, Loy CC. Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(11):7041-7055. doi:10.1109/tpami.2024.3406821

BibTeX
@article{Dai2024,
  author = {Dai, Yuekun and Li, Chongyi and Zhou, Shangchen and Feng, Ruicheng and Luo, Yihang and Loy, Chen Change},
  title = {Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {11},
  pages = {7041--7055},
  doi = {10.1109/tpami.2024.3406821}
}
Kostenlos starten →