# DeepIR: A Deep Semantics Driven Framework for Image Retargeting

arXiv: https://arxiv.org/abs/1811.07793 · HTML: https://mlsanity.com/paper/1811.07793/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2018.

## Built on by (most cited first, 7 of 7)

- [Fast Hybrid Image Retargeting](https://mlsanity.com/paper/2203.13595/) (2022)
- [Prune and Repaint: Content-Aware Image Retargeting for any Ratio](https://mlsanity.com/paper/2410.22865/) (2024)
- [Retargeting video with an end-to-end framework](https://mlsanity.com/paper/2311.04458/) (2023)
- [Screentone-Preserved Manga Retargeting](https://mlsanity.com/paper/2203.03396/) (2022)
- [Supervised Deep Learning for Content-Aware Image Retargeting with Fourier Convolutions](https://mlsanity.com/paper/2306.07383/) (2023)
- [3D Shape Augmentation with Content-Aware Shape Resizing](https://mlsanity.com/paper/2405.09050/) (2024)
- [AttenIR: Aligning Dense Visual Attention with Mesh Warping for Unsupervised Image Retargeting](https://mlsanity.com/paper/2610.17743/) (2026)

## Abstract (arXiv)

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.