Kangfu MEI 梅 康夫

I am a third-year Ph.D. student (2021 - 2025*) at Johns Hopkins University , advised by Prof. Vishal Patel , where I work on compute vision and computational photography. I got my M.Phil degree (2019 - 2021) at The Chinese University of Hong Kong, Shenzhen, advised by Prof. Rui Huang.

I'm working as a Student Researcher at Google Research (Jun 2023 - Now).

I previously interned at: Adobe Research  /  DAMO Academy  /  Kuaishou  /  JD.COM

Email  /  Google Scholar  /  Github  /  Photography

profile photo
Research

My research interest mainly focuses on degraded images restoration as well as its applicatoin in high-level vision. Representative papers are highlighted.

CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
Kangfu Mei, Mauricio Delbracio, Hossein Talebi, Zhengzhong Tu, Vishal M. Patel, Peyman Milanfar,
CVPR 2024
Project Page / arXiv

Faster conditional diffusion that produces high-quality images with 1-4 sampling steps.

LTT-GAN: Looking Through Turbulence by Inverting GANs
Kangfu Mei, Vishal M. Patel
IEEE Journal of Selected Topics in Signal Processing, 2023 [IF: 7.695]
arXiv

The first turbulence mitigation algorithm that can clearly recover face images captured in a range of 300 meters long.

VIDM: Video Implicit Diffusion Models
Kangfu Mei, Vishal M. Patel,
AAAI, 2023 Oral Presentation
Project Page / arXiv

Video Generation Diffusion Models By Using Implicit Motiion Condition.

Deep Semantic Statistics Matching (D2SM) Denoising Network
Kangfu Mei, Vishal M. Patel, Rui Huang
ECCV, 2022
Project Page / arXiv / poster

A New General Plug-and-play Component For Denoising

AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing
Qi Song, Kangfu Mei, Rui Huang
AAAI, 2021
code / arXiv

Two novel Strip Attention Module (SAM) and Attention Fusion Module (AFM) are proposed for enhancing the accuracy of semantic segmentation networks with limited computational complexity increasing. , espcically the scenes contains vertical strip areas

Multi-scale Residual Network for Image Super-resolution
Juncheng Li, Faming Fang, Kangfu Mei, Guixu Zhang
ECCV, 2018
code / bibtex

Introduce a novel multi-scale residual network for recovering the high-quality image from low-resolution.

Service

Reviewer for CVPR, ICCV, ECCV, WACV, ICPR

Reviewer of International Journal of Computer Vision (IJCV)

Reviewer of IEEE Transactions on Image Processing (TIP)

Reviewer of IEEE Transactions on Multimedia (TMM)

Reviewer of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

Reviewer of Computer Vision and Image Understanding (CVIU)

Prizes

AIM2019 Mobile Raw to DSLR RGB Image Mapping Challenge (ICCV2019 Workshop): Top 1

Alibaba Youku Video Enhancement and Super-Resolution Challenge 2019: Top 4

NTIRE2018 Image Dehazing Challenge (CVPR2018 Workshop): Honorable Mention Award & Top 6

University Computer Software Programming Challenge 2018 in The Pearl River Delta: Gold Award & Best innovative Award