Sam-adapter: Adapting segment anything in underperformed scenes
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 …
advancements to AI research. One such model is Segment Anything (SAM), which is …
Automatic shadow detection and removal from a single image
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 …
from a single image. Previous works on shadow detection put a lot of effort in designing …
Automatic feature learning for robust shadow detection
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 …
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 …
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 …
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 …
from specific domains. However, shadow detection on broader image domains is still …
Large scale shadow annotation and detection using lazy annotation and stacked CNNs
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 …
from specific domains. However, shadow detection on broader image domains is still …
[HTML][HTML] Time-lapse ratios of cone excitations in natural scenes
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 …
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
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 …
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 …
accuracy due to highlight reflection noise from users' glasses. To address this, we present a …