Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

Chunle GUO, Chongyi LI, Jichang GUO, Chen Change LOY, Junhui HOU, Sam KWONG, Runmin CONG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

997 Citations (Scopus)

Abstract

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estimation is specially designed, considering pixel value range, monotonicity, and differentiability. Zero-DCE is appealing in its relaxed assumption on reference images, i.e., it does not require any paired or unpaired data during training. This is achieved through a set of carefully formulated non-reference loss functions, which implicitly measure the enhancement quality and drive the learning of the network. Our method is efficient as image enhancement can be achieved by an intuitive and simple nonlinear curve mapping. Despite its simplicity, we show that it generalizes well to diverse lighting conditions. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively. Furthermore, the potential benefits of our Zero-DCE to face detection in the dark are discussed.
Original languageEnglish
Title of host publicationProceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Pages1777-1786
Number of pages10
ISBN (Electronic)9781728171692
ISBN (Print)9781728171685
DOIs
Publication statusPublished - Jun 2020
Externally publishedYes
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020) - Virtual, Seattle, United States
Duration: 14 Jun 202019 Jun 2020
https://cvpr2020.thecvf.com/

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)
Country/TerritoryUnited States
CitySeattle
Period14/06/2019/06/20
Internet address

Bibliographical note

This research was supported by NSFC (61771334,61632018,61871342), SenseTime-NTU Collaboration Project, Singapore MOE AcRF Tier 1 (2018-T1-002-056), NTU SUG, NTU NAP, Fundamental Research Funds for the Central Universities (2019RC039), China Postdoctoral Science Foundation (2019M660438), Hong Kong RGG (9048123) (CityU 21211518), Hong Kong GRF-RGC General Research Fund (9042322,9042489,9042816).

Fingerprint

Dive into the research topics of 'Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement'. Together they form a unique fingerprint.

Cite this