Feifan Lv

I am currently a third-year master student at Beihang University, where I work on computational photography under the supervision of Prof. Feng Lu.

I was a research intern at MSRA, supervised by Dr. Xun Guo. I did my bachelors at Nanjing Agricultural University.

Email  /  Google Scholar  /  Github

profile photo

I'm interested in computational photography, computer vision and image processing. To be specific, I'm particularly interested in low-level vision tasks including denoising, enhancement and super-resolution.

Attention-guided Low-light Image Enhancement
Feifan Lv, Yu Li, Feng Lu
Under Review
project page

By introducing two attention maps to guide the exposure enhancement and denoising tasks respectively, our enhancement network can work an input adaptive way.

Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
Haiyang Si, Zhiqiang Zhang, Feifan Lv, Gang Yu, Feng Lu
Under Review

To achieve fast and accurate perception, we propose an efficient CNN called Multiply Spatial Fusion Network (MSFNet) using Class Boundary Supervision.

An Integrated Enhancement Solution for 24-hour Colorful Imaging
Feifan Lv, Yinqiang Zheng, Yicheng Li, Feng Lu
AAAI, 2020   (Oral Presentation)

To produces clear color images in 24 hours, we separate the VIS and NIR information from mixed signals, and enhance the VIS signal adaptively with the NIR signal as assistance.

Turn a Silicon Camera into an InGaAs Camera
Feifan Lv, Yinqiang Zheng, Bohan Zhang, Feng Lu
CVPR, 2019

To approximate the response of the InGaAs sensor by exploiting the largely ignored sensitivity of a Silicon sensor, weak as it is, in the SWIR range.

Pathological Evidence Exploration in Deep Retinal Image Diagnosis
Yuhao Niu, Lin Gu, Feng Lu, Feifan Lv, Zongji Wang, Imari Sato, Zijian Zhang, Yangyan Xiao, Xunzhang Dai, Tingting Cheng
AAAI, 2019

Inspired by Koch's Postulates, we define a pathological descriptor and propose a GAN based method to visualize the symptom and feature encoded in this descriptor.

MBLLEN: Low-light Image/Video Enhancement Using CNNs
Feifan Lv, Feng Lu, Jianhua Wu, Chongsoon Lim
BMVC, 2018
project page / code

Enhancing low-light image/video using the proposed multi-branch network by extracting and fusing rich features up to different levels.

Last update: Dec. 2019  |  Template stolen from Jon Barron