Conventionally, image denoising and high-level vision tasks are handled separately in computer vision. In this paper, we cope with the two jointly and explore the mutual influence between them. First we propose a convolutional neural network for image denoising which achieves the state-of-theart performance. Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation. We demonstrate that on one hand, the proposed denoiser has the generality to overcome the performance degradation of different high-level vision tasks. On the other hand, with the guidance of highlevel vision information, the denoising network can generate more visually appealing results. To the best of our knowledge, this is the first work investigating the benefit of exploiting image semantics simultaneously for image denoising and high-level vision tasks via deep learning. The code is available online 1 .

No abstract

No abstract

No abstract

We propose and numerically demonstrate a secure key distribution scheme based on the dynamic chaos synchronization of two external cavity vertical-cavity surface-emitting lasers (VCSELs) subject to symmetric random-polarization injections. By exchanging the random parameters that control the polarization angles of the driving injection, Alice and Bob can identify the time slots in which high-quality private chaos synchronization is achieved and independently generate a shared key from the synchronized polarization difference signals of their local VCSELs. The results show that Gb/s key distribution with a low bit error ratio can be achieved, and the shared key can pass all NIST tests, which guarantee the randomness of the key. In the proposed scheme, the exchange messages do not contain any information about the key generation, which affords a high-level of security for key distribution.