Relative Learning from Web Images for Content-adaptive Enhancement
This addresses the need for scalable image enhancement in social media and mobile computing, though it is incremental as it builds on ranking models.
The paper tackles the problem of personalized and content-adaptive image enhancement by introducing a relative-learning-based approach that trains a ranking model from web images without needing matched original-enhanced pairs, resulting in user preference over existing methods in subjective tests.
Personalized and content-adaptive image enhancement can find many applications in the age of social media and mobile computing. This paper presents a relative-learning-based approach, which, unlike previous methods, does not require matching original and enhanced images for training. This allows the use of massive online photo collections to train a ranking model for improved enhancement. We first propose a multi-level ranking model, which is learned from only relatively-labeled inputs that are automatically crawled. Then we design a novel parameter sampling scheme under this model to generate the desired enhancement parameters for a new image. For evaluation, we first verify the effectiveness and the generalization abilities of our approach, using images that have been enhanced/labeled by experts. Then we carry out subjective tests, which show that users prefer images enhanced by our approach over other existing methods.