Image Restoration of Night Time Hazy Images.

Date of Submission

December 2020

Date of Award

Winter 12-12-2021

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science


Computer Vision and Pattern Recognition Unit (CVPR-Kolkata)


Palit, Sarbani (CVPR-Kolkata; ISI)

Abstract (Summary of the Work)

Image restoration is the operation of taking a corrupt/noisy image and estimating the clean, original image. There are various source of noise in image like fog, haze, glow, scattering of light, motion blur and camera misfocus. Image restoration involve various methods to restore images to original form like image dehazing, image denoising, image super-resolution. Images acquired by a visual system are seriously degraded under hazy and foggy weather, which will affect the detection, tracking, and recognition of targets. Thus, restoring the true scene from such a foggy image is of significance. But we focus on Nighttime scenes, which however commonly include visible lights sources with varying colors. These light sources also often introduce noticeable amounts of glow that is not present in daytime images. So in this work we illustrate you with night and day time image dehazing models and our approach of image denoising which also comes under image restoration. In night time image dehazing we illustrate you by CNN model used in various methods and in Image denoising by Auto-encoder.


ProQuest Collection ID:

Control Number


Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


This document is currently not available here.