DeepIR: A Deep Semantics Driven Framework for Image Retargeting
Introduction
We present Deep Image Retargeting (DeepIR), a coarse-to-fine framework for content-aware image retargeting. Our framework first constructs the semantic structure of input image with a deep convolutional neural network. Then a uniform re-sampling that suits for semantic structure preserving is devised to resize feature maps to target aspect ratio at each feature layer. The final retargeting result is generated by coarse-to-fine nearest neighbor field search and step-by-step nearest neighbor field fusion. We empirically demonstrate the effectiveness of our model with both qualitative and quantitative results on widely used RetargetMe dataset.
Paper
Jianxin Lin, Tiankuang Zhou, Zhibo Chen*, "DeepIR: A Deep Semantics Driven Framework for Image Retargeting", In IEEE International Conference on Multimedia and Expo Workshop (ICMEW), 2019.
Download
To get the source code, Please fill THIS FORM and the source code will be sent to you.