Single image layer separation using relative smoothness
This paper addresses extracting two layers from an image where one layer is smoother than
the other. This problem arises most notably in intrinsic image decomposition and reflection …
the other. This problem arises most notably in intrinsic image decomposition and reflection …
Multi-illuminant estimation with conditional random fields
Most existing color constancy algorithms assume uniform illumination. However, in real-
world scenes, this is not often the case. Thus, we propose a novel framework for estimating …
world scenes, this is not often the case. Thus, we propose a novel framework for estimating …
Design of spacecraft missions to remove multiple orbital debris objects
The amount of hazardous debris in Earth orbit has been increasing, posing an ever-greater
danger to space assets and crewed missions. In January of 2007, a Chinese ASAT test …
danger to space assets and crewed missions. In January of 2007, a Chinese ASAT test …
Unsupervised intrinsic image decomposition using internal self-similarity cues
Recent learning-based intrinsic image decomposition methods have achieved remarkable
progress. However, they usually require massive ground truth intrinsic images for …
progress. However, they usually require massive ground truth intrinsic images for …
Smartshadow: Artistic shadow drawing tool for line drawings
L Zhang, J Jiang, Y Ji, C Liu - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
SmartShadow is a deep learning application for digital painting artists to draw shadows on
line drawings, with three proposed tools.(1) Shadow brush: artists can draw scribbles to …
line drawings, with three proposed tools.(1) Shadow brush: artists can draw scribbles to …
Intrinsic layer based automatic specular reflection detection in endoscopic images
Endoscopic images are used to observe the internal structure of the human body. Specular
reflection (SR) images are mostly a consequence of the strong light and bright regions …
reflection (SR) images are mostly a consequence of the strong light and bright regions …
Generating digital painting lighting effects via RGB-space geometry
L Zhang, E Simo-Serra, Y Ji, C Liu - ACM Transactions on Graphics …, 2020 - dl.acm.org
We present an algorithm to generate digital painting lighting effects from a single image. Our
algorithm is based on a key observation: Artists use many overlapping strokes to paint …
algorithm is based on a key observation: Artists use many overlapping strokes to paint …
Single‐image shadow detection and removal using local colour constancy computation
X Yuan, M Ebner, Z Wang - IET Image Processing, 2015 - Wiley Online Library
This study is concerned with the problem of shadow detection and removal from single
images of natural scenes. In this work, the authors propose a shadow detection method with …
images of natural scenes. In this work, the authors propose a shadow detection method with …
Pedestrian color naming via convolutional neural network
Color serves as an important cue for many computer vision tasks. Nevertheless, obtaining
accurate color description from images is non-trivial due to varying illumination conditions …
accurate color description from images is non-trivial due to varying illumination conditions …
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 …