Light the Way: An Enhanced Generative Adversarial Network Framework for Night-to-Day Image Translation With Improved Quality Article Swipe

MAKE IMPACT

H. K. I. S. Lakmal , Maheshi B. Dissanayake , Supavadee Aramvith · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.1109/access.2024.3491792

Driving at night introduces considerable challenges due to reduced visibility, making it essential to explore techniques that enhance road information for drivers. With this purview, the research presents a technique to address visibility constraints faced during night-time driving, by converting night-time road images to day-time images using a supervised Generative Adversarial Network (GAN) model (NtD-GAN). Since paired images are required to train supervised GAN models, the research first exploits a novel approach for generating paired night-day datasets, as it is practically infeasible to collect such image pairs in a natural setting, owing to dynamic traffic environments. An innovative generator network architecture is proposed for the NtD-GAN. Furthermore, a new approach was proposed for generating and loading initial weights to expedite the NtD-GAN training. This initial weight assignment resulted in faster convergence of the NtD-GAN with significant improvement in Inception Score (IS) by 17.3%, in Structural Similarity Index (SSIM) by 5.5%, and in Naturalness Image Quality Evaluator (NIQE) by 10.3%. Moreover, the perceptual loss is introduced to the training loss function of the NtD-GAN to increase the visual quality of the reconstructed images. The experimental results also demonstrated a 0.23% increment in IS, a 0.07% reduction in Fréchet Inception Distance (FID), a 2.2% increment in SSIM, and a 7% reduction in Blind Referenceless Image Spatial Quality Evaluator (BRISQUE) compared to the NtD-GAN trained without perceptual loss. The comparison analysis with the benchmark models has demonstrated a significant improvement. For instance, in comparison to N2D-GAN, NtD-GAN has demonstrated a reduction in FID by 14.6%, an improvement in SSIM by 3.4%, an improvement in Peak Signal-to-Noise Ratio (PSNR) by 1.39 dB and a reduction in BRISQUE by 0.8%. The implementation of the NtD-GAN model is available at https://github.com/isurushanaka/paired-N2D.

Type

article

Language

en

Landing Page

https://doi.org/10.1109/access.2024.3491792

OA Status

gold

Cited By

2

References

90

Related Works

10

OpenAlex ID

https://openalex.org/W4404056951

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4404056951

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.1109/access.2024.3491792

Digital Object Identifier

Title

Light the Way: An Enhanced Generative Adversarial Network Framework for Night-to-Day Image Translation With Improved Quality

Work title

Type

article

OpenAlex work type

Language

en

Primary language

Publication year

2024

Year of publication

Publication date

2024-01-01

Full publication date if available

Authors

H. K. I. S. Lakmal, Maheshi B. Dissanayake, Supavadee Aramvith

List of authors in order

Landing page

https://doi.org/10.1109/access.2024.3491792

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

gold

Open access status per OpenAlex

OA URL

https://doi.org/10.1109/access.2024.3491792

Direct OA link when available

Concepts

Image translation, Computer science, Translation (biology), Adversarial system, Image quality, Quality (philosophy), Image (mathematics), Generative adversarial network, Artificial intelligence, Generative grammar, Speech recognition, Computer vision, Chemistry, Philosophy, Biochemistry, Epistemology, Messenger RNA, Gene

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2025: 2

Per-year citation counts (last 5 years)

References (count)

90

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload