activity
20242026
collaborators
Showing 2025Show all

6 papers · 1 filter

cs.CV2025

Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation

Wei Dong, Han Zhou, Junwei Lin +1

Real-world dark images commonly exhibit not only low visibility and contrast but also complex noise and blur, posing significant restoration challenges. Existing methods often rely…

cs.CV2025

AU-IQA: A Benchmark Dataset for Perceptual Quality Assessment of AI-Enhanced User-Generated Content

Shushi Wang, Chunyi Li, Zicheng Zhang +5

AI-based image enhancement techniques have been widely adopted in various visual applications, significantly improving the perceptual quality of user-generated content (UGC). Howev…

cs.CV2025

Retinex-guided Histogram Transformer for Mask-free Shadow Removal

Wei Dong, Han Zhou, Seyed Amirreza Mousavi +1

While deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalizat…

cs.CV2025

Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design

Wei Dong, Yan Min, Han Zhou +1

Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumin…

cs.CV2025

LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors

Han Zhou, Wei Dong, Jun Chen

Directly employing 3D Gaussian Splatting (3DGS) on images with adverse illumination conditions exhibits considerable difficulty in achieving high-quality, normally-exposed represen…

cs.IT2025

Constrained Gaussian Wasserstein Optimal Transport with Commutative Covariance Matrices

Jun Chen, Jia Wang, Ruibin Li +4

Optimal transport has found widespread applications in signal processing and machine learning. Among its many equivalent formulations, optimal transport seeks to reconstruct a rand…