Publications (12)
Learning to See in the Extremely Dark
Hai Jiang, Binhao Guan, Zhen Liu +5
Learning-based methods have made promising advances in low-light RAW image enhancement, while their capability to extremely dark scenes where the environmental illuminance drops as…
R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
Jiang Hai, Zhu Xuan, Songchen Han +4
Images captured in weak illumination conditions could seriously degrade the image quality. Solving a series of degradation of low-light images can effectively improve the visual qu…
ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models
Hai Jiang, Zhen Liu, Yinjie Lei +3
In this paper, we propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination degradation image restoration, which decouples the restoration process into a…
Unlocking the Performance Potential of Mega-Constellation Networks: An Exploration of Structure-Building Paradigms
Xiangtong Wang, Wei Li, Menglong Yang +1
Mega-constellation networks (MCNs) are transforming global internet access by providing ubiquitous connectivity to millions of users worldwide. The design of MCNs is crucial for ac…
Investigating Inter-Satellite Link Spanning Patterns on Networking Performance in Mega-constellations
Xiangtong Wang, Xiaodong Han, Menglong Yang +4
Low Earth orbit (LEO) mega-constellations rely on inter-satellite links (ISLs) to provide global connectivity. We note that in addition to the general constellation parameters, the…
Supervised Homography Learning with Realistic Dataset Generation
Hai Jiang, Haipeng Li, Songchen Han +3
In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised…
Space Networking Kit: A Novel Simulation Platform for Emerging LEO Mega-constellations
Xiangtong Wang, Xiaodong Han, Menglong Yang +2
This paper presents SNK, a novel simulation platform designed to evaluate the network performance of constellation systems for global Internet services. SNK offers realtime communi…
LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
Hai Jiang, Ao Luo, Xiaohong Liu +2
In this paper, we propose a diffusion-based unsupervised framework that incorporates physically explainable Retinex theory with diffusion models for low-light image enhancement, na…
Multi-Protocol Location Forwarding (MPLF) for Space Routing
Xiangtong Wang, Menglong Yang, Songchen Han +1
The structure and routing architecture design is critical for achieving low latency and high capacity in future LEO space networks (SNs). Existing studies mainly focus on topologie…
Monte Carlo Throughput Estimation in Unstable LEO Satellite Networks
Xiangtong Wan, Menglong Yang, Wei Li +1
This study introduces a new framework for analyzing capacity dynamics and throughput performance in Low Earth Orbit satellite networks (LSNs). It focuses on addressing critical gap…
Low-Light Image Enhancement with Wavelet-based Diffusion Models
Hai Jiang, Ao Luo, Songchen Han +2
Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration.…
Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint
Hai Jiang, Haipeng Li, Yuhang Lu +2
Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strate…