Abstract
Image cropping aims to find visually appealing crops in an image, which is an important yet challenging task. In this paper, we consider a specific and practical application: human-centric image cropping, which focuses on the depiction of a person. To this end, we propose a human-centric image cropping method with two novel feature designs for the candidate crop: partition-aware feature and content-preserving feature. For partition-aware feature, we divide the whole image into nine partitions based on the human bounding box and treat different partitions in a candidate crop differently conditioned on the human information. For content-preserving feature, we predict a heatmap indicating the important content to be included in a good crop, and extract the geometric relation between the heatmap and a candidate crop. Extensive experiments demonstrate that our method can perform favorably against state-of-the-art image cropping methods on human-centric image cropping task. Code is available at https://github.com/bcmi/Human-Centric-Image-Cropping.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ardizzone, E., et al.: Saliency based image cropping. In: ICIAP (2013)
Cavalcanti, C.S.V.C., et al.: Combining multiple image features to guide automatic portrait cropping for rendering different aspect ratios. In: SITIS (2010)
Chen, H., Wang, B., Pan, T., Zhou, L., Zeng, H.: CropNet: real-time thumbnailing. In: ACMMM (2018)
Chen, J., Bai, G., Liang, S., Li, Z.: Automatic image cropping: a computational complexity study. In: CVPR (2016)
Chen, Y.L., Huang, T.W., Chang, K.H., Tsai, Y.C., Chen, H.T., Chen, B.Y.: Quantitative analysis of automatic image cropping algorithms: a dataset and comparative study. In: WACV (2017)
Chen, Y.L., Klopp, J., Sun, M., Chien, S.Y., Ma, K.L.: Learning to compose with professional photographs on the web. In: ACMMM (2017)
Chen, Z., Xu, Q., Cong, R., Huang, Q.: Global context-aware progressive aggregation network for salient object detection. In: AAAI (2020)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)
Deng, Y., Loy, C.C., Tang, X., et al.: Image aesthetic assessment: an experimental survey. IEEE Signal Process. Mag. 34(4), 80–106 (2017)
Esmaeili, S.A., Singh, B., Davis, L.S.: Fast-AT: fast automatic thumbnail generation using deep neural networks. In: CVPR (2017)
Fang, C., Lin, Z., Mech, R., Shen, X.: Automatic image cropping using visual composition, boundary simplicity and content preservation models. In: ACMMM (2014)
Freeman, M.: The photographer’s eye: Composition and design for better digital photos. CRC Press (2007)
Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. PAMI 10(34), 1915–1926 (2012)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)
Hong, C., Du, S., Xian, K., Lu, H., Cao, Z., Zhong, W.: Composing photos like a photographer. In: CVPR (2021)
Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.H.: Deeply supervised salient object detection with short connections. In: CVPR (2017)
Hou, X., Zhang, L.: Saliency detection: a spectral residual approach. In: CVPR (2007)
Kao, Y., et al.: Automatic image cropping with aesthetic map and gradient energy map. In: ICASSP (2017)
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32–73 (2017)
Li, D., Wu, H., Zhang, J., Huang, K.: A2-RL: aesthetics aware reinforcement learning for image cropping. In: CVPR (2018)
Li, D., Wu, H., Zhang, J., Huang, K.: Fast A3RL: aesthetics-aware adversarial reinforcement learning for image cropping. TIP 28(10), 5105–5120 (2019)
Li, D., Zhang, J., Huang, K.: Learning to learn cropping models for different aspect ratio requirements. In: CVPR (2020)
Li, D., Zhang, J., Huang, K., Yang, M.H.: Composing good shots by exploiting mutual relations. In: CVPR (2020)
Li, Q., et al.: Deeper insights into graph convolutional networks for semi-supervised learning. In: AAAI (2018)
Li, X., Li, X., Zhang, G., Zhang, X.: Image aesthetic assessment using a saliency symbiosis network. J. Electron. Imaging 28(2), 023008 (2019)
Li, Z., Zhang, X.: Collaborative deep reinforcement learning for image cropping. In: ICME (2019)
Lu, P., Zhang, H., Peng, X., Jin, X.: An end-to-end neural network for image cropping by learning composition from aesthetic photos (2019)
Lu, W., Xing, X., Cai, B., Xu, X.: Listwise view ranking for image cropping. IEEE Access 7, 91904–91911 (2019)
Mai, L., et al.: Composition-preserving deep photo aesthetics assessment. In: CVPR (2016)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. PAMI 39, 1137–1149 (2015)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Networks 20(1), 61–80 (2008)
She, D., Lai, Y.K., Yi, G., Xu, K.: Hierarchical layout-aware graph convolutional network for unified aesthetics assessment. In: CVPR (2021)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015)
Su, Y.C., et al.: Camera view adjustment prediction for improving image composition. arXiv preprint arXiv:2104.07608 (2021)
Sun, J., Ling, H.: Scale and object aware image thumbnailing. IJCV 104(2), 135–153 (2013)
Tu, Y., Niu, L., Zhao, W., Cheng, D., Zhang, L.: Image cropping with composition and saliency aware aesthetic score map. In: AAAI (2020)
Vig, E., Dorr, M., Cox, D.: Large-scale optimization of hierarchical features for saliency prediction in natural images. In: CVPR (2014)
Wang, W., Shen, J.: Deep cropping via attention box prediction and aesthetics assessment. In: ICCV (2017)
Wang, W., Shen, J., Ling, H.: A deep network solution for attention and aesthetics aware photo cropping. PAMI 41(7), 1531–1544 (2018)
Wei, Z., et al.: Good view hunting: learning photo composition from dense view pairs. In: CVPR (2018)
Yan, J., Lin, S., Bing Kang, S., Tang, X.: Learning the change for automatic image cropping. In: CVPR (2013)
Zeng, H., Li, L., Cao, Z., Zhang, L.: Reliable and efficient image cropping: a grid anchor based approach. In: CVPR (2019)
Zeng, H., Li, L., Cao, Z., Zhang, L.: Grid anchor based image cropping: a new benchmark and an efficient model. PAMI PP(01) (2020)
Zhang, L., Song, M., Yang, Y., Zhao, Q., Zhao, C., Sebe, N.: Weakly supervised photo cropping. TMM 16(1), 94–107 (2013)
Zhang, L., Song, M., Zhao, Q., Liu, X., Bu, J., Chen, C.: Probabilistic graphlet transfer for photo cropping. TIP 22(2), 802–815 (2012)
Zhang, M., Zhang, L., Sun, Y., Feng, L., Ma, W.: Auto cropping for digital photographs. In: ICME (2005)
Zhang, X., Li, Z., Constable, M., Chan, K.L., Tang, Z., Tang, G.: Pose-based composition improvement for portrait photographs. IEEE Trans. Circuits Syst. Video Technol. 29(3), 653–668 (2018)
Zhang, Y., Sun, X., Yao, H., Qin, L., Huang, Q.: Aesthetic composition represetation for portrait photographing recommendation. In: ICIP (2012)
Zhao, T., Wu, X.: Pyramid feature attention network for saliency detection. In: CVPR (2019)
Acknowledgement
The work is supported by Shanghai Municipal Science and Technology Key Project (Grant No. 20511100300), Shanghai Municipal Science and Technology Major Project, China (2021SHZDZX0102), and National Science Foundation of China (Grant No. 61902247).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, B., Niu, L., Zhao, X., Zhang, L. (2022). Human-Centric Image Cropping with Partition-Aware and Content-Preserving Features. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13667. Springer, Cham. https://doi.org/10.1007/978-3-031-20071-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-20071-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20070-0
Online ISBN: 978-3-031-20071-7
eBook Packages: Computer ScienceComputer Science (R0)