EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Focusing on your subject: Deep subject-aware image composition recommendation networks

Guo-Ye Yang, Wen-Yang Zhou, Yun Cai, Song-Hai Zhang, Fang-Lue Zhang

Computational Visual Media · 2023-03 · 9 (1) · 87-107

DOI: 10.1007/s41095-021-0263-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Visual Media, 2023-03. Verfasst von Guo-Ye Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Photo composition is one of the most important factors in the aesthetics of photographs. As a popular application, composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-learning-based composition recommendation approaches. In this paper, we propose a subject-aware image composition recommendation method, SAC-Net, which takes an RGB image and a binary subject window mask as input, and returns good compositions as crops containing the subject. Our model first determines candidate scores for all possible coarse cropping windows. The crops with high candidate scores are selected and further refined by regressing their corner points to generate the output recommended cropping windows. The final scores of the refined crops are predicted by a final score regression module. Unlike existing methods that need to preset several cropping windows, our network is able to automatically regress cropping windows with arbitrary aspect ratios and sizes. We propose novel stability losses for maximizing smoothness when changing cropping windows along with view changes. Experimental results show that our method outperforms state-of-the-art methods not only on the subject-aware image composition recommendation task, but also for general purpose composition recommendation. We also have designed a multistage labeling scheme so that a large amount of ranked pairs can be produced economically. We use this scheme to propose the first subject-aware composition dataset SACD, which contains 2777 images, and more than 5 million composition ranked pairs. The SACD dataset is publicly available at https://cg.cs.tsinghua.edu.cn/SACD/ .

Zitieren

APA

Yang, G., Zhou, W., Cai, Y., Zhang, S., & Zhang, F. (2023). Focusing on your subject: Deep subject-aware image composition recommendation networks. Computational Visual Media, 9(1), 87-107. https://doi.org/10.1007/s41095-021-0263-3

Vancouver

Yang G, Zhou W, Cai Y, Zhang S, Zhang F. Focusing on your subject: Deep subject-aware image composition recommendation networks. Computational Visual Media. 2023;9(1):87-107. doi:10.1007/s41095-021-0263-3

BibTeX
@article{Yang2023,
  author = {Yang, Guo-Ye and Zhou, Wen-Yang and Cai, Yun and Zhang, Song-Hai and Zhang, Fang-Lue},
  title = {Focusing on your subject: Deep subject-aware image composition recommendation networks},
  journal = {Computational Visual Media},
  year = {2023},
  volume = {9},
  number = {1},
  pages = {87--107},
  doi = {10.1007/s41095-021-0263-3}
}
Kostenlos starten →