Qingnan Fan

I am a PhD student in the Computer Science and Technology School of Shandong University since 2014. I am supervised by Prof. Baoquan Chen.

I visited Tel Aviv University, Hebrew University of Jerusalem several times between 2014 to 2015 to work with Prof. Daniel Cohen-Or and Prof. Dani Lischinski.

I was a research intern in the Visual Computing Group of MSRA supervised by David Wipf from Sept. 2016 to Feb. 2018. I also collaborated with Xin Tong, Gang Hua and Jiaolong Yang while in MSR.

I was also a research intern in the Advanced Innovation Center for Future Visual Entertainment led by Prof. Baoquan Chen, in Beijing Film Academy between Mar. 2018 and Aug. 2019.

I am currently a post-doctoral researcher in Stanford University supervised by Prof. Leonidas Guibas.

Email  /  CV  /  Biography

Research

My research interest mainly lies in computer vision, image processing, video processing, computational photography. I'm specifically interested in interactive real-time video segmentation, reflection removal, image smoothing, intrinsic image decomposition, and practical application of my developed techniques on mobile devices.

RainFlow: Optical Flow under Rain Streaks and Rain Veiling Effect
Ruoteng Li, Robby T. Tan, Loong-Fah Cheong, Angelica I. Aviles-Rivero, Qingnan Fan, Carola-bibiane Schönlieb.
ICCV, 2019
arXiv

A deep-learning based optical flow approach designed to handle heavy rain.

A General Decoupled Learning Framework for Parameterized Image Operators
Qingnan Fan*, Dongdong Chen*, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen.
TPAMI, 2019
arXiv / codes / demo / bibtex

A journal extension of our ECCV 2018 paper. We further propose a cheap parameter-tuning version of the decouple learning framework that enables real-time alternation between different image operators.

GraphXNET - Chest X-Ray Classification Under Extreme Minimal Supervision
Angelica Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Qingnan Fan, Robby Tan, Carola-Bibiane Schönlieb.
MICCAI, 2019
bibtex

A novel semi-supervised framework for X-ray classification which is based on a graph-based optimisation model. A new multi-class classification functional that strengthens the synergy between the limited number of labels and the huge amount of unlabelled data.

Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All? - A Tailored Approach to Single Image Reflection Removal
Daniel Heydecker*, Georg Maierhofer*, Angelica Aviles-Rivero*, Qingnan Fan, Dongdong Chen, Carola-Bibiane Schönlieb, Sabine Süsstrunk.
TIP, 2019
bibtex

A simple and tractable user interactive tool for single image reflection removal, which is facilitated with a spatially-aware prior term solved by an efficient half-quadratic splitting optimization approach.

Gated Context Aggregation Network for Image Dehazing and Deraining
Dongdong Chen, Mingming He, Qingnan Fan, Jing Liao, Liheng Zhang, Dongdong Hou, Lu Yuan, Gang Hua.
WACV, 2019
arXiv / codes / bibtex

A novel end-to-end gated context aggregation network GCANet that outperforms all the existing appraoches by a large margin on both image dehazing and deraining tasks.

Image Smoothing via Unsupervised Learning
Qingnan Fan, Jiaolong Yang, David Wipf, Baoquan Chen, Xin Tong.
SIGGRAPH Asia, 2018
arXiv / codes / supp file / bibtex

Treat deep learning as an optimization tool to minimize the proposed image smoothing objective function in an unsupervised manner. Multiple different smoothing effects can be easily learned by adaptively changing the proposed objective function.

Decouple Learning for Parameterized Image Operators
Qingnan Fan*, Dongdong Chen*, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen.
ECCV , 2018
arXiv / codes / supp file / poster / bibtex

The first decouple learning framework that is capable of successfully incorporating many different parameterized image operators into a single network without requirement of retraining or fintuning any other networks.

Revisiting Deep Intrinsic Image Decompositions
Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Wipf.
CVPR , 2018 (Oral)
arXiv / codes / slides / supp file / poster / presentation (start from 36:44) / bibtex

The first demonstration of a single basic deep architecture capable of achieving state-of-the-art results when applied to each of the major intrinsic benchmarks.

A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Wipf.
ICCV, 2017
arXiv / codes / supp file / poster / bibtex

An advanced deep architecture for low-level vision tasks; A novel reflection image synthesis approach which enables outstanding generalization ability to real images with trained newtork.

JumpCut: Non-Successive Mask Transfer and Interpolation for Video Cutout
Qingnan Fan, Fan Zhong, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen.
SIGGRAPH Asia, 2015
codes / slides / video / supp file / dataset / bibtex

An interactive real-time video segmentation algorithm. Significantly improve the video cutout accuracy and efficiency.

Build-to-Last: Strength to Weight 3D Printed Objects
Lin Lu, Andrei Sharf, Haisen Zhao, Yuan Wei, Qingnan Fan, Xuelin Chen, Yann Savoye, Changhe Tu, Daniel Cohen-Or, Baoquan Chen.
SIGGRAPH, 2014
video / bibtex

Reduce the material cost and weight of a given object while providing a durable printed model that is resistant to impact and external forces.