“Automatic Photo-from-Panorama for Google Maps”
Conference:
Type:
Entry Number: 74
Title:
- Automatic Photo-from-Panorama for Google Maps
Presenter(s)/Author(s):
Abstract:
We introduce a technique for extracting interesting photographs from 360° panoramas. We build on the success of convolutional neural networks for classification to train a model that scores a given view, using this score to find a best view. Training data for this classification model is generated automatically from landmark detections within Street View panoramas. We validate that our selected views are often preferred over manually chosen ones and have experienced an increase in user interaction when automatically selected views are shown on Google Maps.
References:
S. Dhar, V. Ordonez, and T.L. Berg. 2011. High level describable attributes for predicting aesthetics and interestingness. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. 1657–1664.
Hui Fang and Meng Zhang. 2017. Creatism: A deep-learning photographer capable of creating professional work. CoRR abs/1707.03491 (2017). arXiv:1707.03491 http://arxiv.org/abs/1707.03491
P. Isola, Jianxiong Xiao, D. Parikh, A. Torralba, and A. Oliva. 2014. What Makes a Photograph Memorable? Pattern Analysis and Machine Intelligence, IEEE Transactions on 36, 7 (July 2014), 1469–1482.
Luming Zhang, Mingli Song, Yi Yang, Qi Zhao, Chen Zhao, and N. Sebe. 2014. Weakly Supervised Photo Cropping. Multimedia, IEEE Transactions on 16, 1 (Jan 2014), 94–107.
