Aerial image dehazing with attentive deformable transformers

A Kulkarni, S Murala - Proceedings of the IEEE/CVF Winter …, 2023 - openaccess.thecvf.com
Aerial imagery is widely utilized in visual data dependent applications such as military
surveillance, earthquake assessment, etc. For these applications, minute texture in the aerial …

A survey of deep learning-based image restoration methods for enhancing situational awareness at disaster sites: the cases of rain, snow and haze

S Karavarsamis, I Gkika, V Gkitsas, K Konstantoudakis… - Sensors, 2022 - mdpi.com
This survey article is concerned with the emergence of vision augmentation AI tools for
enhancing the situational awareness of first responders (FRs) in rescue operations. More …

Dual-frame spatio-temporal feature modulation for video enhancement

PW Patil, S Gupta, S Rana, S Venkatesh - Pattern Recognition, 2022 - Elsevier
Current video enhancement approaches have achieved good performance in specific rainy,
hazy, foggy, and snowy weather conditions. However, they currently suffer from two …

Unified multi-weather visibility restoration

A Kulkarni, PW Patil, S Murala… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Automated surveillance is widely opted for appli-cations such as traffic monitoring, vehicle
identification, etc. But, various weather degradation factors such as rain and snow streaks …

NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction

B Lin, Y Jin, W Yan, W Ye, Y Yuan, S Zhang… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Existing deep-learning-based methods for nighttime video deraining rely on synthetic data
due to the absence of real-world paired data. However, the intricacies of the real world …

Nested deformable multi-head attention for facial image inpainting

SS Phutke, S Murala - Proceedings of the IEEE/CVF Winter …, 2023 - openaccess.thecvf.com
Extracting adequate contextual information is an important aspect of any image inpainting
method. To achieve this, ample image inpainting methods are available that aim to focus on …

Lrnet: lightweight recurrent network for video dehazing

VM Galshetwar, PW Patil, S Chaudhary - Signal, Image and Video …, 2023 - Springer
The presence of hazy particles affects visibility and disturbs the color balance in the
captured videos. Thus, video dehazing is a challenging pre-processing step for high-level …

Cross-stage recurrent feature sharing network for video dehazing

VM Galshetwar, P Saini, S Chaudhary - Expert Systems with Applications, 2024 - Elsevier
Hazy weather conditions feed serious haze effects, such as color and visibility degradations
in the captured videos. Extensive research on video dehazing has been carried out …

IDSSI: Image Deturbulence with Semantic and Spatial–Temporal Information

X Liu, L Tang, G Li, Z Zhang, S Yan, Y Xiao, J Xie… - Pattern Recognition, 2024 - Elsevier
The propagation of light through turbulent media results in refractive index fluctuations,
causing distortion and blurring of images captured by imaging equipment. Consequently, it …

C2AIR: Consolidated Compact Aerial Image Haze Removal

A Kulkarni, SS Phutke, SK Vipparthi… - Proceedings of the …, 2024 - openaccess.thecvf.com
Aerial image haze removal deals with improving the visibility and quality of images captured
from aerial platforms, such as drones and satellites. Aerial images are commonly used in …