CVNov 19, 2018

DeepIR: A Deep Semantics Driven Framework for Image Retargeting

arXiv:1811.07793v326 citations
Originality Incremental advance
AI Analysis

This work addresses content-aware image resizing for applications like web design or media adaptation, but it appears incremental as it builds on existing retargeting methods with a new deep learning approach.

The authors tackled image retargeting by proposing DeepIR, a coarse-to-fine framework that uses deep convolutional neural networks to preserve semantic structure, achieving effectiveness demonstrated with qualitative and quantitative results on the RetargetMe dataset.

We present \emph{Deep Image Retargeting} (\emph{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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes