collaborators

5 papers

cs.CV2026

BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration

Qianliang Wu, Haobo Jiang, Guangwei Gao +5

Reliable matching between partially observed, deforming point clouds requires global context and fine geometric detail. Coarse candidate selection can exclude correct fine-level co…

cs.CV2026

WaveFreqAnchor: Wave-Structural Anchoring and Frequency Correction Diffusion for Training-Free Face Restoration

Zelin Du, Wenjie Li, Zhengxue Wang +3

Diffusion-based face restoration that adjusts the sampling trajectory of pre-trained diffusion models has achieved remarkable progress. However, existing approaches provide insuffi…

cs.CV2026

PASDiff: Physics-Aware Semantic Guidance for Joint Real-World Low-Light Face Enhancement and Restoration

Yilin Ni, Wenjie Li, Zhengxue Wang +3

Face images captured in real-world low light suffer multiple degradations-low illumination, blur, noise, and low visibility, etc. Existing cascaded solutions often suffer from seve…

cs.CV2025

Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba

Liwen Pan, Longguang Wang, Guangwei Gao +3

Traffic image restoration under adverse weather conditions remains a critical challenge for intelligent transportation systems. Existing methods primarily focus on spatial-domain m…

cs.CV2025

Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration

Wenjie Li, Yulun Zhang, Guangwei Gao +2

Blind face restoration (BFR) may correspond to multiple plausible high-quality (HQ) reconstructions under extremely low-quality (LQ) inputs. However, existing methods typically pro…