# Object-IR: Leveraging Object Consistency and Mesh Deformation for Self-Supervised Image Retargeting

arXiv: https://arxiv.org/abs/2510.27236 · HTML: https://mlsanity.com/paper/2510.27236/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [Parallax-Tolerant Unsupervised Deep Image Stitching](https://mlsanity.com/paper/2302.08207/) (2023)
- [Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation](https://mlsanity.com/paper/2107.02524/) (2021)
- [Generating natural images with direct Patch Distributions Matching](https://mlsanity.com/paper/2203.11862/) (2022)
- [Deep Rectangling for Image Stitching: A Learning Baseline](https://mlsanity.com/paper/2203.03831/) (2022)
- [Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting](https://mlsanity.com/paper/1708.02731/) (2017)
- [Cycle-IR: Deep Cyclic Image Retargeting](https://mlsanity.com/paper/1905.03556/) (2019)
- [Deep Rotation Correction without Angle Prior](https://mlsanity.com/paper/2207.03054/) (2022)
- [MOWA: Multiple-in-One Image Warping Model](https://mlsanity.com/paper/2404.10716/) (2024)
- [Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2503.20826/) (2025)
- [Image Resizing by Reconstruction from Deep Features](https://mlsanity.com/paper/1904.08475/) (2019)
- [Retargeting Visual Data with Deformation Fields](https://mlsanity.com/paper/2311.13297/) (2023)

## Built on by (most cited first, 1 of 1)

- [AttenIR: Aligning Dense Visual Attention with Mesh Warping for Unsupervised Image Retargeting](https://mlsanity.com/paper/2610.17743/) (2026)

## Abstract (arXiv)

Eliminating geometric distortion in semantically important regions remains an intractable challenge in image retargeting. This paper presents Object-IR, a self-supervised architecture that reformulates image retargeting as a learning-based mesh warping optimization problem, where the mesh deformation is guided by object appearance consistency and geometric-preserving constraints. Given an input image and a target aspect ratio, we initialize a uniform rigid mesh at the output resolution and use a convolutional neural network to predict the motion of each mesh grid and obtain the deformed mesh. The retargeted result is generated by warping the input image according to the rigid mesh in the input image and the deformed mesh in the output resolution. To mitigate geometric distortion, we design a comprehensive objective function incorporating a) object-consistent loss to ensure that the important semantic objects retain their appearance, b) geometric-preserving loss to constrain simple scale transform of the important meshes, and c) boundary loss to enforce a clean rectangular output. Notably, our self-supervised paradigm eliminates the need for manually annotated retargeting datasets by deriving supervision directly from the input's geometric and semantic properties. Extensive evaluations on the RetargetMe benchmark demonstrate that our Object-IR achieves state-of-the-art performance, outperforming existing methods in quantitative metrics and subjective visual quality assessments. The framework efficiently processes arbitrary input resolutions (average inference time: 0.009s for 1024x683 resolution) while maintaining real-time performance on consumer-grade GPUs. The source code will soon be available at https://github.com/tlliao/Object-IR.