Chen, Y.-C.Y.-C.ChenChang, K.-J.K.-J.ChangTsai, Y.-H.Y.-H.TsaiYU-CHIANG WANGChiu, W.-C.W.-C.Chiu2021-05-052021-05-052020https://www.scopus.com/inward/record.url?eid=2-s2.0-85087333350&partnerID=40&md5=e35fec86f2c216469486649b4cc59687https://scholars.lib.ntu.edu.tw/handle/123456789/559363In 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 is directly optimized in order to satisfy saliency-guidance. Extensive experiments verify the capacity of our model in saliency-driven image editing and show favorable performance against numerous baselines. © 2019. The copyright of this document resides with its authors.Computer vision; Conventional approach; Estimation methods; Guided images; Image editing; Image manipulation; Image regions; Learning Based Models; Low-level features; Deep learningconference paper2-s2.0-85087333350