Find me a sky : a data-driven method for color-consistent sky search & replacement
- A novel approach for aesthetic enhancement of an image with a dull background by replacing it's sky using a data-driven method for sky search and replacement.
- Curated dataset of 1246 images with interesting and appealing skies.
- Identified relevant features helpful in color consistent sky search.
- Quantative and qualitative proof for the hypothesis that images with matching foreground color properties can have interchangeble backgrounds.
- Saumya Rawat, Siddhartha Gairola, Rajvi Shah, and P J Narayanan Find me a sky : a data-driven method for color-consistent sky search & replacement, International Conference on Multimedia Modeling (MMM), February 5-7, 2018. [ Paper ] [ Slides ]
The dataset consists of 1246 images with corresponding binary masks indicating sky and non-sky regions in the folders image and mask respectively. It has been curated from 415 Flickr images with diverse skies (collected by ) and 831 outdoor images curated from the ADE20K Dataset. ADE20K dataset consists of ∼ 22K images with 150 semantic categories like sky, road, grass. The images with sky category were first filtered to a set of ∼6K useful images for which the sky region made > 40% of the total image. These images were manually rated between 1 to 5 for aesthetic appeal of the skies by two human raters and only the images with average scores higher than 3 were added to the final dataset
Download : Dataset
If you use this work or dataset, please cite :
Rawat S., Gairola S., Shah R., Narayanan P.J. (2018) Find Me a Sky: A Data-Driven Method for Color-Consistent Sky Search and Replacement. In: Schoeffmann K. et al. (eds) MultiMedia Modeling. MMM 2018. Lecture Notes in Computer Science, vol 10704. Springer, Cham
- Saumya Rawat
- Siddhartha Gairola
- Rajvi Shah
- P J Narayanan
- Y.-H. Tsai, X. Shen, Z. Lin, K. Sunkavalli, and M.-H. Yang Sky is not the limit: Semantic aware sky replacement. ACM Trans. Graph, 35(4), 2016.
- Bolei Zhou, Hang Zhao, Xavier Puig, Sanja Fidler, Adela Barriuso, and Antonio Torralba Scene parsing through ade20k dataset, In Proc. IEEE CVPR, 2017.