Guide Your Eyes: Learning Image Manipulation under Saliency Guidance

Yen-Chung Chen (National Chiao Tung University), Keng-Jui Chang (National Chiao Tung University), Yi-Hsuan Tsai (NEC Labs America), Yu-Chiang Frank Wang (National Taiwan University), Wei-Chen Chiu (National Chiao Tung University)

Abstract
In this paper, we tackle the problem of saliency-guided image manipulation for adjusting the saliency distribution over image regions. Conventional approaches ordinarily utilize explicit operations on altering the low-level features based on the selected saliency computation. However, it is difficult to generalize such methods for various saliency estimations. To address this issue, we propose a deep learning-based model that bridges between any differentiable saliency estimation methods and a neural network which applies image manipulation. Thus, the manipulation can be directly optimized in order to satisfy saliency-guidance. Extensive experiment results verify the capacity of our model in saliency-driven image editing and show favorable performance against numerous baselines.

DOI
10.5244/C.33.24
https://dx.doi.org/10.5244/C.33.24

Files
Paper (PDF)
Supplementary material (ZIP)

BibTeX