Jian Wang

Howard Zhang, Yuval Alaluf, Sizhuo Ma et al.

Face image restoration aims to enhance degraded facial images while addressing challenges such as diverse degradation types, real-time processing demands, and, most crucially, the preservation of identity-specific features. Existing methods often struggle with slow processing times and suboptimal restoration, especially under severe degradation, failing to accurately reconstruct finer-level identity details. To address these issues, we introduce InstantRestore, a novel framework that leverages a single-step image diffusion model and an attention-sharing mechanism for fast and personalized face restoration. Additionally, InstantRestore incorporates a novel landmark attention loss, aligning key facial landmarks to refine the attention maps, enhancing identity preservation. At inference time, given a degraded input and a small (~4) set of reference images, InstantRestore performs a single forward pass through the network to achieve near real-time performance. Unlike prior approaches that rely on full diffusion processes or per-identity model tuning, InstantRestore offers a scalable solution suitable for large-scale applications. Extensive experiments demonstrate that InstantRestore outperforms existing methods in quality and speed, making it an appealing choice for identity-preserving face restoration.

Jian-min Wang, Tian-yu Xie, Hong-fei Zhang et al.

We present a high-quality, bias-free quantum random number generator (QRNG) using photon arrival time selectively in accordance with the number of photon detection events within a sampling time interval in attenuated light. It is well showed in both theoretical analysis and experiments verification that this random number production method eliminates both bias and correlation perfectly without more post processing and the random number can clearly pass the standard randomness tests. We fulfill theoretical analysis and experimental verification of the method whose rate can reach up to 45Mbps.

Hong-fei Zhang, Jian Wang, Ke Cui et al.

A real-time Quantum Key Distribution System is developed in this paper. In the system, based on the feature of Field Programmable Gate Array (FPGA), secure key extraction control and algorithm have been optimally designed to perform sifting, error correction and privacy amplification altogether in real-time. In the QKD experiment information synchronization mechanism and high-speed classic data channel are designed to ensure the steady operation of the system. Decoy state and synchronous laser light source are used in the system, while the length of optical fiber between Alice and Bob is 20 km. With photons repetition frequency of 20 MHz, the final key rate could reach 17 kbps. Smooth and robust operation is verified with 6-hour continuous test and associated with encrypted voice communication test.