Haze removal from an image via generative adversarial networks
The performance of computer vision applications like autonomous vehicles, satellite imaging can get affected by real-world conditions such as haze, smoke and rain particles. Recent works focus on using deep-learning GAN-based and Transformer-based model for image dehazing. However, current methods s...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/174985 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-174985 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1749852024-04-19T15:44:57Z Haze removal from an image via generative adversarial networks Cheng, Mun Chew Loke Yuan Ren School of Computer Science and Engineering yrloke@ntu.edu.sg Computer and Information Science The performance of computer vision applications like autonomous vehicles, satellite imaging can get affected by real-world conditions such as haze, smoke and rain particles. Recent works focus on using deep-learning GAN-based and Transformer-based model for image dehazing. However, current methods still stuggle to generate realistic and structurally accurate dehazed images. Hence, this study propose to incorporate structuralsimilarity loss and GAN adversarial loss into the training process to further improve realism and structural accuracy of the dehazed image. As such, an improved version of the Dehazeformer [14] is introduced in this paper by integrating SSIM loss and adversarial loss into the feedback training. Experiments were conducted on the RESIDE Benchmark Dataset [17] and the NTIRE challenge datasets [18-20]. The experiments displayed a 0.62%, improvement in Indoor Images PSNR, 0.1%/0.1% improvement in BRISQUE and NIQE score as well. Object detection experiments also showed my model performed better than the original Dehazeformer by an average of 0.07%. Bachelor's degree 2024-04-18T02:06:24Z 2024-04-18T02:06:24Z 2024 Final Year Project (FYP) Cheng, M. C. (2024). Haze removal from an image via generative adversarial networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/174985 https://hdl.handle.net/10356/174985 en SCSE23-0566 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science |
spellingShingle |
Computer and Information Science Cheng, Mun Chew Haze removal from an image via generative adversarial networks |
description |
The performance of computer vision applications like autonomous vehicles, satellite imaging can get affected by real-world conditions such as haze, smoke and rain particles. Recent works focus on using deep-learning GAN-based and Transformer-based model for image dehazing. However, current methods still stuggle to generate realistic and structurally accurate
dehazed images. Hence, this study propose to incorporate structuralsimilarity
loss and GAN adversarial loss into the training process to further
improve realism and structural accuracy of the dehazed image. As
such, an improved version of the Dehazeformer [14] is introduced in this paper by integrating SSIM loss and adversarial loss into the feedback training. Experiments were conducted on the RESIDE Benchmark Dataset [17] and the NTIRE challenge datasets [18-20]. The experiments displayed a
0.62%, improvement in Indoor Images PSNR, 0.1%/0.1% improvement in BRISQUE and NIQE score as well. Object detection experiments also showed my model performed better than the original Dehazeformer by an average of 0.07%. |
author2 |
Loke Yuan Ren |
author_facet |
Loke Yuan Ren Cheng, Mun Chew |
format |
Final Year Project |
author |
Cheng, Mun Chew |
author_sort |
Cheng, Mun Chew |
title |
Haze removal from an image via generative adversarial networks |
title_short |
Haze removal from an image via generative adversarial networks |
title_full |
Haze removal from an image via generative adversarial networks |
title_fullStr |
Haze removal from an image via generative adversarial networks |
title_full_unstemmed |
Haze removal from an image via generative adversarial networks |
title_sort |
haze removal from an image via generative adversarial networks |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/174985 |
_version_ |
1814047150478196736 |