Results 41 to 50 of about 210,130 (70)
Some of the next articles are maybe not open access.
IEEE International Conference on Computer Vision, 2023
Shadows often occur when we capture the document with casual equipment, which influences the visual quality and readability of the digital copies. Different from the algorithms for natural shadow removal, the algorithms in document shadow removal need to
Zinuo Li +3 more
semanticscholar +1 more source
Shadows often occur when we capture the document with casual equipment, which influences the visual quality and readability of the digital copies. Different from the algorithms for natural shadow removal, the algorithms in document shadow removal need to
Zinuo Li +3 more
semanticscholar +1 more source
NTIRE 2023 Image Shadow Removal Challenge Report
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023This work reviews the results of the NTIRE 2023 Challenge on Image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consists of 1200 roughly pixel aligned pairs
Florin-Alexandru Vasluianu +103 more
semanticscholar +1 more source
A Shadow Imaging Bilinear Model and Three-Branch Residual Network for Shadow Removal
IEEE Transactions on Neural Networks and Learning Systems, 2023The current shadow removal pipeline relies on the detected shadow masks, which have limitations for penumbras and tiny shadows, and results in an excessively long pipeline.
Jiawei Liu +4 more
semanticscholar +1 more source
Bijective Mapping Network for Shadow Removal
Computer Vision and Pattern Recognition, 2022Shadow removal, which aims to restore the background in the shadow regions, is challenging due to its highly ill-posed nature. Most existing deep learning-based methods individually remove the shadow by only considering the content of the matched paired ...
Yurui Zhu +5 more
semanticscholar +1 more source
Shadow care infrastructures: Sustaining life in post-welfare cities
Progress in Human Geography, 2022Economic restructuring and welfare reform are driving new forms of urban poverty in the global north. Shadow care infrastructures is a new frame for conceptualising the complex and interconnected practices through which marginalised people seek survival ...
Emma R. Power +3 more
semanticscholar +1 more source
Single Image Shadow Detection via Complementary Mechanism
ACM Multimedia, 2022In this paper, we present a novel shadow detection framework by investigating the mutual complementary mechanisms contained in this specific task.
Yurui Zhu +5 more
semanticscholar +1 more source
Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting
IEEE International Conference on Computer Vision, 2021Although CNNs have achieved remarkable progress on the shadow detection task, they tend to make mistakes in dark non-shadow regions and relatively bright shadow regions. They are also susceptible to brightness change.
Lei Zhu +3 more
semanticscholar +1 more source
A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection
Computer Vision and Pattern Recognition, 2020Existing shadow detection methods suffer from an intrinsic limitation in relying on limited labeled datasets, and they may produce poor results in some complicated situations.
Zhihao Chen +5 more
semanticscholar +1 more source
Testing the nature of Gauss–Bonnet gravity by four-dimensional rotating black hole shadow
The European Physical Journal Plus, 2020The recent discovery of the novel four-dimensional static and spherically symmetric Gauss–Bonnet black hole provides a promising bed to test Gauss–Bonnet gravity by using astronomical observations (Glavan et al. in PRL 124:081301, 2020).
Shao-Wen Wei, Yu-Xiao Liu
semanticscholar +1 more source
ARShadowGAN: Shadow Generative Adversarial Network for Augmented Reality in Single Light Scenes
Computer Vision and Pattern Recognition, 2020Generating virtual object shadows consistent with the real-world environment shading effects is important but challenging in computer vision and augmented reality applications.
Daquan Liu +5 more
semanticscholar +1 more source