# Cycle-IR: Deep Cyclic Image Retargeting

arXiv: https://arxiv.org/abs/1905.03556 · HTML: https://mlsanity.com/paper/1905.03556/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2019.

## Built on by (most cited first, 14 of 14)

- [Instance-Level Relative Saliency Ranking with Graph Reasoning](https://mlsanity.com/paper/2107.03824/) (2021)
- [Deep Rotation Correction without Angle Prior](https://mlsanity.com/paper/2207.03054/) (2022)
- [Retargeting Visual Data with Deformation Fields](https://mlsanity.com/paper/2311.13297/) (2023)
- [Fast Hybrid Image Retargeting](https://mlsanity.com/paper/2203.13595/) (2022)
- [OAIR: Object-Aware Image Retargeting Using PSO and Aesthetic Quality Assessment](https://mlsanity.com/paper/2209.04804/) (2022)
- [Dense Multitask Learning to Reconfigure Comics](https://mlsanity.com/paper/2307.08071/) (2023)
- [Retargeting video with an end-to-end framework](https://mlsanity.com/paper/2311.04458/) (2023)
- [HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations](https://mlsanity.com/paper/2504.03026/) (2025)
- [Object-IR: Leveraging Object Consistency and Mesh Deformation for Self-Supervised Image Retargeting](https://mlsanity.com/paper/2510.27236/) (2025)
- [Screentone-Preserved Manga Retargeting](https://mlsanity.com/paper/2203.03396/) (2022)
- [Saliency-aware Stereoscopic Video Retargeting](https://mlsanity.com/paper/2304.08852/) (2023)
- [Supervised Deep Learning for Content-Aware Image Retargeting with Fourier Convolutions](https://mlsanity.com/paper/2306.07383/) (2023)
- [Taming Reversible Halftoning via Predictive Luminance](https://mlsanity.com/paper/2306.08309/) (2023)
- [AttenIR: Aligning Dense Visual Attention with Mesh Warping for Unsupervised Image Retargeting](https://mlsanity.com/paper/2610.17743/) (2026)

## Abstract (arXiv)

Supervised deep learning techniques have achieved great success in various fields due to getting rid of the limitation of handcrafted representations. However, most previous image retargeting algorithms still employ fixed design principles such as using gradient map or handcrafted features to compute saliency map, which inevitably restricts its generality. Deep learning techniques may help to address this issue, but the challenging problem is that we need to build a large-scale image retargeting dataset for the training of deep retargeting models. However, building such a dataset requires huge human efforts. In this paper, we propose a novel deep cyclic image retargeting approach, called Cycle-IR, to firstly implement image retargeting with a single deep model, without relying on any explicit user annotations. Our idea is built on the reverse mapping from the retargeted images to the given input images. If the retargeted image has serious distortion or excessive loss of important visual information, the reverse mapping is unlikely to restore the input image well. We constrain this forward-reverse consistency by introducing a cyclic perception coherence loss. In addition, we propose a simple yet effective image retargeting network (IRNet) to implement the image retargeting process. Our IRNet contains a spatial and channel attention layer, which is able to discriminate visually important regions of input images effectively, especially in cluttered images. Given arbitrary sizes of input images and desired aspect ratios, our Cycle-IR can produce visually pleasing target images directly. Extensive experiments on the standard RetargetMe dataset show the superiority of our Cycle-IR. In addition, our Cycle-IR outperforms the Multiop method and obtains the best result in the user study. Code is available at https://github.com/mintanwei/Cycle-IR.