2017 · 251 citations · 27 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningImage EditingImage SynthesisScene ConstructionScene UnderstandingHand-crafted FeaturesImage CompositingSemantic InformationTraining
Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have focused on learning statistical relationships between hand-crafted appearance features of the foreground and background, which is unreliable especially when the contents in the two layers are vastly different. In this work, we propose an end-to-end deep convolutional neural network for image harmonization, which can capture both the context and semantic information of the composite images during harmonization. We also introduce an efficient way to collect large-scale and high-quality training data that can facilitate the training process. Experiments on the synthesized dataset and real composite images show that the proposed network outperforms previous state-of-the-art methods.
27
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
Yangqing Jia, Evan Shelhamer, Jeff Donahue et al. · 2014 · 11.2K citations
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia, Evan Shelhamer, Jeff Donahue et al. · arXiv (Cornell University) · 2014 · 4.3K citations · Full text