Abstract:

Adjusting photographs to obtain compelling renditions requires skill and time. Even contrast and brightness adjustments are challenging because they require taking into account the image content. Photographers are also known for having different retouching preferences. As the result of this complexity, rule-based, one-size-fits-all automatic techniques often fail. This problem can greatly benefit from supervised machine learning but the lack of training data has impeded work in this area. Our first contribution is the creation of a high-quality reference dataset. We collected 5,000 photos, manually annotated them, and hired 5 trained photographers to retouch each picture. The result is a collection of 5 sets of 5,000 example input-output pairs that enable supervised learning. We first use this dataset to predict a user's adjustment from a large training set. We then show that our dataset and features enable the accurate adjustment personalization using a carefully chosen set of training photos. Finally, we introduce difference learning: this method models and predicts difference between users. It frees the user from using predetermined photos for training. We show that difference learning enables accurate prediction using only a handful of examples.

Publication:

• V. Bychkovsky, S. Paris, E. Chan, and F. Durand. "Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs" IEEE Computer Vision and Pattern Recognition (CVPR). June 2011, Colorado Springs, CO.
  • - PDF
  • - BibTeX
  • - Demo Video
  • - MIT-Adobe FiveK Dataset
  • - Figure 2 was produced with the following list of training and testing image IDs. These IDs were randomly selected. Test set errors of our method (CDF in Figure 2) can found here.
  • - 2.5k images adjusted by our algorithm. Format: 8-bit PNG, colorspace: sRGB. Note that only luminance in these images is produced by our algorithm. Color infomration is copied from the expert.

Acknowledgments: