papers

Publications (6)

cs.CV2026

Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement

Xiaoran Sun, Liyan Wang, Yeying Jin +5

Most existing low-light image enhancement (LLIE) methods rely on pre-trained model priors, low-light inputs, or both, while neglecting the semantic guidance available from normal-l…

cs.CV2022

Restoration of User Videos Shared on Social Media

Hongming Luo, Fei Zhou, Kin-man Lam +1

User videos shared on social media platforms usually suffer from degradations caused by unknown proprietary processing procedures, which means that their visual quality is poorer t…

cs.CV2026

MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model

Wanshu Fan, Xiangyu Li, Cong Wang +4

Images captured by consumer electronic devices, such as mobile phones and digital cameras, often suffer from low-light degradation due to sensor limitations and imaging pipelines,…

cs.CV2025

HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding

Yiqing Yang, Yun Li, Kin-Man Lam +6

Key frame selection is essentially a set-level optimization problem: the quality of the selected subset depends on the interactions among frames, rather than the score of any singl…

cs.CV2024

IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater

Jingchun Zhou, Qilin Gai, Kin-man Lam +1

In underwater environments, variations in suspended particle concentration and turbidity cause severe image degradation, posing significant challenges to image enhancement (IE) and…

cs.CV2021

Progressive and Selective Fusion Network for High Dynamic Range Imaging

Qian Ye, Jun Xiao, Kin-man Lam +1

This paper considers the problem of generating an HDR image of a scene from its LDR images. Recent studies employ deep learning and solve the problem in an end-to-end fashion, lead…