GANmera: Reproducing aesthetically pleasing photographs using deep adversarial networks

Nelson Chong, Lai-Kuan Wong, John See

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Generative adversarial networks (GANs) have become increasingly popular in recent years owing to its ability to synthesize and transfer. The image enhancement task can also be modeled as an image-to-image translation problem. In this paper, we propose GANmera, a deep adversarial network which is capable of performing aesthetically-driven enhancement of photographs. The network adopts a 2-way GAN architecture and is semi-supervised with aesthetic-based binary labels (good and bad). The network is trained with unpaired image sets, hence eliminating the need for strongly supervised before-after pairs. Using CycleGAN as the base architecture, several fine-grained modifications are made to the loss functions, activation functions and resizing schemes, to achieve improved stability in the generator. Two training strategies are devised to produce results with varying aesthetic output. Quantitative evaluation on the recent benchmark MIT-Adobe-5K dataset demonstrate the capability of our method in achieving state-of-the-art PSNR results. We also show qualitatively that the proposed approach produces aesthetically-pleasing images. This work is a shortlisted submission to the CVPR 2019 NTIRE Image Enhancement Challenge.

Original languageEnglish
Title of host publication2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
PublisherIEEE
Pages2179-2187
Number of pages9
ISBN (Electronic)9781728125060
DOIs
Publication statusPublished - 9 Apr 2020
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops 2019
Abbreviated titleCVPRW 2019
Country/TerritoryUnited States
CityLong Beach
Period16/06/1920/06/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'GANmera: Reproducing aesthetically pleasing photographs using deep adversarial networks'. Together they form a unique fingerprint.

Cite this