Sam-adapter: Adapting segment anything in underperformed scenes

T Chen, L Zhu, C Deng, R Cao… - Proceedings of the …, 2023 - openaccess.thecvf.com
The emergence of large models, also known as foundation models, has brought significant
advancements to AI research. One such model is Segment Anything (SAM), which is …

Automatic shadow detection and removal from a single image

SH Khan, M Bennamoun, F Sohel… - IEEE transactions on …, 2015 - ieeexplore.ieee.org
We present a framework to automatically detect and remove shadows in real world scenes
from a single image. Previous works on shadow detection put a lot of effort in designing …

Automatic feature learning for robust shadow detection

SH Khan, M Bennamoun, F Sohel… - 2014 IEEE conference …, 2014 - ieeexplore.ieee.org
We present a practical framework to automatically detect shadows in real world scenes from
a single photograph. Previous works on shadow detection put a lot of effort in designing …

Fast shadow detection from a single image using a patched convolutional neural network

S Hosseinzadeh, M Shakeri… - 2018 IEEE/RSJ …, 2018 - ieeexplore.ieee.org
In recent years, various shadow detection methods from a single image have been
proposed and used in vision systems; however, most of them are not appropriate for the …

Shadow detection and removal for illumination consistency on the road

C Wang, H Xu, Z Zhou, L Deng… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Shadow detection and removal is an important task for on-road visual perception. However,
effectively detecting and removing the shadows on the road to maintain illumination …

Noisy label recovery for shadow detection in unfamiliar domains

TFY Vicente, M Hoai… - Proceedings of the IEEE …, 2016 - openaccess.thecvf.com
Recent shadow detection algorithms have shown initial success on small datasets of images
from specific domains. However, shadow detection on broader image domains is still …

Large scale shadow annotation and detection using lazy annotation and stacked CNNs

L Hou, TFY Vicente, M Hoai… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Recent shadow detection algorithms have shown initial success on small datasets of images
from specific domains. However, shadow detection on broader image domains is still …

[HTML][HTML] Time-lapse ratios of cone excitations in natural scenes

DH Foster, K Amano, SMC Nascimento - Vision research, 2016 - Elsevier
The illumination in natural environments varies through the day. Stable inferences about
surface color might be supported by spatial ratios of cone excitations from the reflected light …

A survey on shadow detection techniques in a single image

S Murali, VK Govindan, S Kalady - Information technology and control, 2018 - itc.ktu.lt
Shadows are inescapable elements in a scene formed due to the presence of an object
between the light source and the surface on which it is cast. Appearance of shadows often …

[HTML][HTML] SF-SAM-Adapter: SAM-based segmentation model integrates prior knowledge for gaze image reflection noise removal

T Lei, J Chen, J Chen - Alexandria Engineering Journal, 2025 - Elsevier
Gaze tracking technology in HMDs (Head-Mounted Displays) suffers from decreased
accuracy due to highlight reflection noise from users' glasses. To address this, we present a …