collaborators

5 papers

cs.CV2025

When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training

Yunwei Lan, Zhigao Cui, Xin Luo +5

Recent advancements in unpaired dehazing, particularly those using GANs, show promising performance in processing real-world hazy images. However, these methods tend to face limita…

cs.CV2025

Latent Posterior-Mean Rectified Flow for Higher-Fidelity Perceptual Face Restoration

Xin Luo, Menglin Zhang, Yunwei Lan +4

The Perception-Distortion tradeoff (PD-tradeoff) theory suggests that face restoration algorithms must balance perceptual quality and fidelity. To achieve minimal distortion while…

cs.CV2025

Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training

Yunwei Lan, Zhigao Cui, Chang Liu +4

Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous stu…

cs.CV2024

NeRF Inpainting with Geometric Diffusion Prior and Balanced Score Distillation

Menglin Zhang, Xin Luo, Yunwei Lan +5

Recent advances in NeRF inpainting have leveraged pretrained diffusion models to enhance performance. However, these methods often yield suboptimal results due to their ineffective…

cs.CV2024

StableV2V: Stablizing Shape Consistency in Video-to-Video Editing

Chang Liu, Rui Li, Kaidong Zhang +2

Recent advancements of generative AI have significantly promoted content creation and editing, where prevailing studies further extend this exciting progress to video editing. In d…