arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.07608cs.CV
收藏

用于改善图像合成的摄像机视角调整预测

Camera View Adjustment Prediction for Improving Image Composition

Google Research(谷歌研究院)

Yu-Chuan Su, Raviteja Vemulapalli, Ben Weiss, Chun-Te Chu, Philip Andrew Mansfield, Lior Shapira, Colvin Pitts

摘要:

图像构图对照片的质量起着重要作用。然而,并不是每个相机用户都拥有拍摄构图良好的照片所需的知识和专业知识。虽然拍摄后裁剪有时可以改善构图,但在许多常见的场景中,摄影师需要调整相机视图以捕捉最佳镜头时,它并不起作用。为了解决这个问题,我们提出了一种基于深度学习的方法,该方法向摄影师提供关于如何在捕获之前调整相机视图的建议。通过在拍摄照片之前优化构图,我们的系统可以帮助摄影师拍摄更好的照片。由于此任务没有公开可用的数据集,我们通过重新利用现有的图像裁剪数据集来创建视图调整数据集。此外,我们提出了一个两阶段的半监督方法,利用标记和未标记的图像训练的视图调整模型。实验结果表明,所提出的半监督的方法优于相应的监督替代品,我们的用户研究结果表明,建议的视图调整提高了79%的时间的图像组成。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑