Camera View Adjustment Prediction for Improving Image Composition
This addresses the issue for amateur photographers who lack expertise in capturing well-composed photos, though it is incremental as it builds on existing image cropping datasets and methods.
The paper tackles the problem of improving image composition by predicting camera view adjustments before photo capture, using a deep learning-based approach that suggests adjustments to photographers. The results show that the suggested view adjustments improve image composition 79% of the time in a user study.
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.