4 papers
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…
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…
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…
HAD-GAN: A Human-perception Auxiliary Defense GAN to Defend Adversarial Examples
Wanting Yu, Hongyi Yu, Lingyun Jiang +2
Adversarial examples reveal the vulnerability and unexplained nature of neural networks. Studying the defense of adversarial examples is of considerable practical importance. Most…