# Learning Subject-Aware Cropping by Outpainting Professional Photos

arXiv: https://arxiv.org/abs/2312.12080 · HTML: https://mlsanity.com/paper/2312.12080/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 24 of its 55 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [3D Ken Burns Effect from a Single Image](https://mlsanity.com/paper/1909.05483/) (2019)
- [Boundless: Generative Adversarial Networks for Image Extension](https://mlsanity.com/paper/1908.07007/) (2019)
- [Very Long Natural Scenery Image Prediction by Outpainting](https://mlsanity.com/paper/1912.12688/) (2019)
- [Reliable and Efficient Image Cropping: A Grid Anchor based Approach](https://mlsanity.com/paper/1904.04441/) (2019)
- [Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study](https://mlsanity.com/paper/1701.01480/) (2017)
- [Learning to Compose with Professional Photographs on the Web](https://mlsanity.com/paper/1702.00503/) (2017)
- [Image Cropping with Composition and Saliency Aware Aesthetic Score Map](https://mlsanity.com/paper/1911.10492/) (2019)
- [Human-centric Image Cropping with Partition-aware and Content-preserving Features](https://mlsanity.com/paper/2207.10269/) (2022)

## Built on by (most cited first, 12 of 12)

- [Cropper: Vision-Language Model for Image Cropping through In-Context Learning](https://mlsanity.com/paper/2408.07790/) (2024)
- [PhotoFramer: Multi-modal Image Composition Instruction](https://mlsanity.com/paper/2512.00993/) (2025)
- [ProCrop: Learning Aesthetic Image Cropping from Professional Compositions](https://mlsanity.com/paper/2505.22490/) (2025)
- [Towards Smart Point-and-Shoot Photography](https://mlsanity.com/paper/2505.03638/) (2025)
- [Photography Perspective Composition: Towards Aesthetic Perspective Recommendation](https://mlsanity.com/paper/2505.20655/) (2025)
- [AesCrop: Aesthetic-driven Cropping Guided by Composition](https://mlsanity.com/paper/2510.22528/) (2025)
- [CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference](https://mlsanity.com/paper/2605.12545/) (2026)
- [ShutterMuse: Capture-Time Photography Guidance with MLLMs](https://mlsanity.com/paper/2606.25763/) (2026)
- [ShotCrop3: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions](https://mlsanity.com/paper/2606.05635/) (2026)
- [COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models](https://mlsanity.com/paper/2606.28696/) (2026)
- [Discrete Annotation, Continuous Preference: Rethinking Supervision for Accurate and Generalizable Aesthetic Image Cropping](https://mlsanity.com/paper/2610.00582/) (2026)
- [FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model](https://mlsanity.com/paper/2610.17639/) (2026)

## Abstract (arXiv)

How to frame (or crop) a photo often depends on the image subject and its context; e.g., a human portrait. Recent works have defined the subject-aware image cropping task as a nuanced and practical version of image cropping. We propose a weakly-supervised approach (GenCrop) to learn what makes a high-quality, subject-aware crop from professional stock images. Unlike supervised prior work, GenCrop requires no new manual annotations beyond the existing stock image collection. The key challenge in learning from this data, however, is that the images are already cropped and we do not know what regions were removed. Our insight is to combine a library of stock images with a modern, pre-trained text-to-image diffusion model. The stock image collection provides diversity and its images serve as pseudo-labels for a good crop, while the text-image diffusion model is used to out-paint (i.e., outward inpainting) realistic uncropped images. Using this procedure, we are able to automatically generate a large dataset of cropped-uncropped training pairs to train a cropping model. Despite being weakly-supervised, GenCrop is competitive with state-of-the-art supervised methods and significantly better than comparable weakly-supervised baselines on quantitative and qualitative evaluation metrics.