A curated list of resources including papers, datasets, and relevant links pertaining to foreground object search. Foreground object search (FOS) aims to retrieve the foreground objects from a candidate set which are compatible with the given background in terms of semantics, geometry, or lightness. For more complete resources on general image composition, please refer to Awesome-Image-Composition.
Contributions are welcome. If you wish to contribute, feel free to send a pull request. If you have suggestions for new sections to be included, please raise an issue and discuss before sending a pull request.
A brief review on foreground object search is included in the following survey on image composition:
Li Niu, Wenyan Cong, Liu Liu, Yan Hong, Bo Zhang, Jing Liang, Liqing Zhang: "Making Images Real Again: A Comprehensive Survey on Deep Image Composition." arXiv preprint arXiv:2106.14490 (2021). [arXiv] [slides]
- Bo Zhang, Jiacheng Sui, Li Niu: "Foreground Object Search by Distilling Composite Image Feature." ICCV (2023) [arXiv][dataset&code]
- Sijie Zhu, Zhe Lin, Scott Cohen, Jason Kuen, Zhifei Zhang, Chen Chen: "GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing." ECCV (2022) [arXiv]
- Zongze Wu, Dani Lischinski, Eli Shechtman: "Fine-grained Foreground Retrieval via Teacher-Student Learning." WACV (2021) [pdf]
- Boren Li, Po-Yu Zhuang, Jian Gu, Mingyang Li, Ping Tan: "Interpretable Foreground Object Search As Knowledge Distillation." ECCV (2020) [arXiv]
- Yinan Zhao, Brian Price, Scott Cohen, Danna Gurari: "Unconstrained foreground object search." ICCV (2019) [pdf]
- Hengshuang Zhao, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Brian Price, Jiaya Jia: "Compositing-aware image search." ECCV (2018) [pdf]
- FOSD: It contains a Real Foreground Object Search Dataset (R-FOSD) and a Synthetic Foreground Object Search Dataset (S-FOSD). [link]