Low-Light Image Enhancement (LLIE) is generally regarded as a challenging task that aims to brighten the low-light images and reduce the noise. Many studies have contributed to the community by applying different technologies, including Retinex-based ones. However, most Retinex-based methods dealt with the LLIE issue in mono-channel decomposition way, leading to the imperfect results. In this work, a novel two-stage convolutional neural network (CNN)-based framework composed of the three-channel Retinex decomposition module and the illumination enhancement module is proposed to deal with the LLIE issue. Inspired by the Retinex theory, the former is optimized by introducing the reflectance consistency loss and the well-designed illumination regularization loss, while the latter is supervised by the parameter loss and the enhancement loss. It has proven more effective and flexible, when comparing with the prevalent mono-channel decomposition approaches, due to the capabilities of illumination adjustment, global optimization and shot noise suppression. Both the quantitative and qualitative experiment results on the Low-Light (LOL) dataset demonstrate the better performance of the proposed three-channel Retinex decomposition network in comparison with other works.
Unsupervised person re-identification (re-ID) aims to identify the same persons' images across different cameras by training on unlabeled data. In which, how to alleviating the occlusion problem in unsupervised person re-ID is a great challenge. Recently, the work on unsupervised re-ID has achieved substantial progress by clustering on the unlabelled target data or unsupervised domain adaptation. Nevertheless, previous re-ID methods either ignored the occlusion problem or solved it based on extreme assumptions. Therefore, in order to develop a kind of more practical and generalized re-ID methods, this paper propose to alleviate the occlusion problem for the unsupervised model. Firstly, we introduce a poseguided branch to extract the key-points information of person. Then, the global feature extracted by backbone and postural feature obtained by pose-guided branch are fused to fed into the unsupervised system. Finally, the experimental results demonstrate that our identification accuracy has achieved strong performance on the three person re-ID dataset.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.