This portal has been archived. Explore the next generation of this technology.
Deep Image Harmonization
lib:d045eb8c02910936 (v1.0.0)
Authors: Yi-Hsuan Tsai,Xiaohui Shen,Zhe Lin,Kalyan Sunkavalli,Xin Lu,Ming-Hsuan Yang
Where published: CVPR 2017 7
ArXiv: 1703.00069
Document: PDF DOI
Artifact development version: GitHub
Abstract URL: http://arxiv.org/abs/1703.00069v1
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.
Where published: CVPR 2017 7
ArXiv: 1703.00069
Document: PDF DOI
Artifact development version: GitHub
Abstract URL: http://arxiv.org/abs/1703.00069v1
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.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)