Sky is Not the Limit: Semantic-Aware Sky Replacement

Yi-Hsuan Tsai    Xiaohui Shen    Zhe Lin    Kalyan Sunkavalli    Ming-Hsuan Yang   

University of California, Merced        Adobe Research

Figure 1. Given an input photograph, the proposed algorithm automatically generates a set of images with stylized skies. The proposed algorithm exploits visual semantics for sky editing, in which scene parsing is first performed on the input image, and such semantic information is utilized for the subsequent steps including sky segmentation, search and replacement.


Skies are common backgrounds in photos but are often less interesting due to the time of photographing. Professional photographers correct this by using sophisticated tools with painstaking efforts that are beyond the command of ordinary users. In this work, we propose an automatic background replacement algorithm that can generate realistic, artifact-free images with a diverse styles of skies. The key idea of our algorithm is to utilize visual semantics to guide the entire process including sky segmentation, search and replacement. First we train a deep convolutional neural network for semantic scene parsing, which is used as visual prior to segment sky regions in a coarse-to-fine manner. Second, in order to find proper skies for replacement, we propose a data-driven sky search scheme based on semantic layout of the input image. Finally, to re-compose the stylized sky with the original foreground naturally, an appearance transfer method is developed to match statistics locally and semantically. We show that the proposed algorithm can automatically generate a set of visually pleasing results. In addition, we demonstrate the effectiveness of the proposed algorithm with extensive user studies.


"Sky is Not the Limit: Semantic-Aware Sky Replacement", Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Ming-Hsuan Yang
ACM Transactions on Graphics (Proc. SIGGRAPH), 2016


author = {Y.-H. Tsai and X. Shen and Z. Lin and K. Sunkavalli and M.-H. Yang},
journal = {ACM Transactions on Graphics (Proc. SIGGRAPH)},
title = {Sky is Not the Limit: Semantic-Aware Sky Replacement},
volume = {35},
number = {4},
year = {2016}}