Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5198-5206
DOI: 10.1609/aaai.v38i6.28326 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xinhao Tao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).
Abstract (Originalsprache)
Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. Moreover, we design a two-stage network named DMASNet with decomposed mask prediction and attentive shadow filling. Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction. In the second stage, we attend to reference background shadow pixels to fill the foreground shadow. Abundant experiments prove that our DMASNet achieves better visual effects and generalizes well to real composite images.
Zitieren
APA
Tao, X., Cao, J., Hong, Y., & Niu, L. (2024). Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5198-5206. https://doi.org/10.1609/aaai.v38i6.28326
Vancouver
Tao X, Cao J, Hong Y, Niu L. Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5198-5206. doi:10.1609/aaai.v38i6.28326
BibTeX
@article{Tao2024,
author = {Tao, Xinhao and Cao, Junyan and Hong, Yan and Niu, Li},
title = {Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {5198--5206},
doi = {10.1609/aaai.v38i6.28326}
}
EUVIMED