Feng Hansen (冯汉森)

I am currently a third-year Ph.D. student at VMCL of Beijing Institute of Technology (BIT). I am reaserching under the supervision of A.P. Lizhi Wang. Before joining BIT, I received my bachelor's degree from University of Science and Technology Beijing (USTB) in 2020.

Email  /  Google Scholar  /  Github

My research interests include computer vision, computational photography, and image processing. I enjoy the research that can benefit real-world applications.

We present a learnability enhancement strategy to reform paired real data according to noise modeling. We demonstrate the superior performance of our methods on public datasets and our dataset in both quantitative results and visual quality.

In this paper, we propose a novel strategy: learning the noise model from dark frames instead of paired real data. Based on the proposed strategy, we introduce an efficient physics-guided noise neural proxy (PNNP) to approximate the real-world sensor noise model. The low data dependency of PNNP exhibits its powerful potential for practical low-light raw image denoising. Extensive experiments on public datasets demonstrate the superiority of our PNNP.

The website template was borrowed from here.
本站总访问量次
本站访客数人次
本文总阅读量次