Giter Club home page Giter Club logo

zero-reference-low-light-image-enhancement's Introduction

Zero-Reference Low-Light Image Enhancement

colab

Low-light image enhancement aims to raise the quality of pictures taken in dim lighting, resulting in a brighter, clearer, and more visually appealing image without adding too much noise or distortion. One of the state-of-the-art methods for this computer vision task is Zero-DCE. This method uses just a low-light image without any image reference to learn how to produce an image with higher brightness. There are four loss functions crafted specifically for this zero-reference low-light image enhancement method, i.e., color constancy loss, exposure loss, illumination smoothness loss, and spatial consistency loss.

Experiment

Open the following link and hit the run all in the colab notebook to examine the overall processes.

Result

Quantitative Result

The quantitative performance of the model is exhibited in the table below.

Metrics Test Dataset
Color Constancy Loss 0.065
Exposure Loss 0.391
Illumination Smoothness Loss 0.094
Spatial Consistency Loss 0.042
Total Loss 0.592
PSNR 13.646
SSIM 0.663
MAE 0.170

Evaluation Metrics Curve

colorconstancy_loss_curve
Color constancy loss curve on the train set and the validation set.

exposure_loss_curve
Exposure loss curve on the train set and the validation set.

illumination_smoothness_loss_curve
Illumination smoothness loss curve on the train set and the validation set.

spatialconsistency_loss_curve
Spatial consistency loss curve on the train set and the validation set.

totalloss_curve
Total loss curve on the train set and the validation set.

psnr_curve
PSNR curve on the train set and the validation set.

ssim_curve
SSIM curve on the train set and the validation set.

mae_curve
MAE curve on the train set and the validation set.

Qualitative Result

Here are some samples of the qualitative results of the model.

enhancement_qualitative_00
enhancement_qualitative_01
enhancement_qualitative_02
The qualitative results of the image enhancement method (comparing the original, the ground-truth, the PIL autocontrast, and the prediction).

Credit

zero-reference-low-light-image-enhancement's People

Contributors

reshalfahsi avatar

Stargazers

 avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.