Abstract

Image enhancement is an inherently subjective process since people have diverse preferences for image aesthetics. However, most enhancement techniques pay less attention to the personalization issue despite its importance. In this paper, we propose the first deep learning approach to personalized image enhancement, which can enhance new images for a new user, by asking him or her to select about 10∼20 preferred images from a random set of images. First, we represent various users’ preferences for enhancement as feature vectors in an embedding space, called preference vectors. We construct the embedding space based on metric learning. Then, we develop the personalized image enhancement network (PieNet) to enhance images adaptively using each user’s preference vector. Experimental results demonstrate that the proposed algorithm is capable of achieving personalization successfully, as well as outperforming conventional general image enhancement algorithms significantly. The source codes and trained models are available at https://github.com/hukim1124/PieNet.

(a) Metric learning to model users’ preferences

(b) Personalized image enhancement with perference vectors

Results on the MIT Adobe 5K dataset.

Input

HDR

DPE

DUPE

Proposed B

Photographer B

Proposed C

Photographer C

Results on the expanded MIT Adobe 5K dataset.

Proposed - LDR

Proposed - WVM

Proposed - Red Lift Matte

Proposed - Photographer E

LDR

WVM

Red Lift Matte

Photographer E C

PieNet Demo.

Cite

Links

Paper and Github