Skip to search formSkip to main contentSkip to account menu
Kindling the Darkness: A Practical Low-light Image Enhancer
TLDR
This work builds a simple yet effective network for Kindling the Darkness (denoted as KinD), which, inspired by Retinex theory, decomposes images into two components that are robust against severe visual defects, and user-friendly to arbitrarily adjust light levels.
View on ACM
Beyond Brightening Low-light Images
TLDR
This work builds a simple yet effective network, which, inspired by Retinex theory, decomposes images into two components, followed a divide-and-conquer principle, and is trained with paired images shot under different exposure conditions.
View on Springer
Single Image Deraining: A Comprehensive Benchmark Analysis
TLDR
A comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images, and provides a rich variety of criteria for dehazing algorithm evaluation.
View on IEEE
SPHORB: A Fast and Robust Binary Feature on the Sphere
TLDR
Extensive experiments show that SPHORB consistently outperforms other existing spherical features in accuracy, efficiency and robustness to camera movements, and has been validated by real-world matching tests.
View on Springer
Automatic Generation of Grounded Visual Questions
TLDR
This paper proposes the first model to be able to generate visually grounded questions with diverse types for a single image and shows that the model outperforms the strongest baseline in terms of both correctness and diversity with a wide margin.
View PDF on arXiv
PFLD: A Practical Facial Landmark Detector
TLDR
This paper investigates a neat model with promising detection accuracy under wild environments e.g., unconstrained pose, expression, lighting, and occlusion conditions) and super real-time speed on a mobile device.
View PDF on arXiv
Improvements of Juang 's Password-Authenticated Key Agreement Scheme Using Smart Cards
TLDR
This work proposes an improved scheme to overcome the weaknesses and maintain the benefits of the original scheme, and believes that the improved scheme is more suitable for real-life applications than that of Juang et al.
View on IEEE
Local albedo-insensitive single image dehazing
TLDR
The results demonstrate that the proposed algorithm can produce transmission maps without being affected by the local albedo variations and, furthermore, recover haze-free images.
View on Springer
MIFT: A Mirror Reflection Invariant Feature Descriptor
TLDR
The structure of MIFT is analyzed and it is shown how MIFT outperforms SIFT in the context of mirror reflection while performs as well as SIFT when there is no mirror reflection.
View via Publisher
Chart decoder: Generating textual and numeric information from chart images automatically
View via Publisher
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License