# Relative Learning from Web Images for Content-adaptive Enhancement

## TL;DR

This paper introduces a relative learning approach for content-adaptive image enhancement that leverages large online photo collections without requiring matched training pairs, resulting in improved and user-preferred enhancements.

## Contribution

It proposes a novel multi-level ranking model learned from relatively-labeled data and a parameter sampling scheme for effective image enhancement.

## Key findings

- The approach generalizes well to new images.
- Users prefer images enhanced by this method.
- The method effectively utilizes online photo collections.

## Abstract

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.