Camera View Adjustment Prediction for Improving Image Composition

TL;DR

This paper introduces a deep learning system that predicts camera view adjustments to enhance photo composition before capture, utilizing a novel semi-supervised training method and a new dataset.

Contribution

It presents a semi-supervised learning approach for camera view adjustment prediction and creates a new dataset for this task, improving composition suggestions.

Findings

Semi-supervised approach outperforms supervised models.

View adjustment suggestions improve composition in 79% of cases.

New dataset enables training and evaluation of view adjustment models.

Abstract

Image composition plays an important role in the quality of a photo. However, not every camera user possesses the knowledge and expertise required for capturing well-composed photos. While post-capture cropping can improve the composition sometimes, it does not work in many common scenarios in which the photographer needs to adjust the camera view to capture the best shot. To address this issue, we propose a deep learning-based approach that provides suggestions to the photographer on how to adjust the camera view before capturing. By optimizing the composition before a photo is captured, our system helps photographers to capture better photos. As there is no publicly-available dataset for this task, we create a view adjustment dataset by repurposing existing image cropping datasets. Furthermore, we propose a two-stage semi-supervised approach that utilizes both labeled and unlabeled images for training a view adjustment model. Experiment results show that the proposed semi-supervised approach outperforms the corresponding supervised alternatives, and our user study results show that the suggested view adjustment improves image composition 79% of the time.