7 papers
LUMEN: Low-light Unified Multi-stage Enhancement Network using depth-guided flash, clustering, and attention-based Transformers
Bibhabasu Debnath, Sahana Ray, Sanjay Ghosh
Low-light image enhancement remains a challenging problem due to severe noise, color distortion, contrast degradation, and loss of structural details under insufficient illuminatio…
An Attention-Enhanced Network with Joint Dehazing and Retinex-Based Enhancement for Underwater Images
Sahana Ray, Bibhabasu Debnath, Sanjay Ghosh
Underwater images suffer from severe wavelength-dependent light absorption and scattering, and turbidity due to suspended particles, degrading visual quality for applications in au…
An Underwater Dehazing Network with Implicit Transmission Estimation
Sahana Ray, Sanjay Ghosh
Underwater images suffer from wavelength-dependent light absorption and scattering, which reduces visual quality. This phenomenon could limit the operational reliability of autonom…
Learned Adaptive Kernels for High-Fidelity Image Downscaling
Piyush Narhari Pise, Sanjay Ghosh
Image downscaling is a fundamental operation in image processing, crucial for adapting high-resolution content to various display and storage constraints. While classic methods oft…
High-Quality and Large-Scale Image Downscaling for Modern Display Devices
Suvrojit Mitra, G B Kevin Arjun, Sanjay Ghosh
In modern display technology and visualization tools, downscaling images is one of the most important activities. This procedure aims to maintain both visual authenticity and struc…
Low-Light Image Enhancement Using Gamma Learning And Attention-Enabled Encoder-Decoder Networks
Bibhabasu Debnath, Sahana Ray, Sanjay Ghosh
Images acquired in low-light environments present significant obstacles for computer vision systems and human perception, especially for applications requiring accurate object reco…
Poisson Informed Retinex Network for Extreme Low-Light Image Enhancement
Isha Rao, Ratul Chakraborty, Sanjay Ghosh
Low-light image denoising and enhancement are challenging, especially when traditional noise assumptions, such as Gaussian noise, do not hold in majority. In many real-world scenar…