Lu FANG 方璐

Ph.D, Associate Professor
Dept. of Electronic Engineering, Tsinghua University

Research Interests: Computational Photography and Visual Intelligence
E-mail: fanglu at tsinghua.edu.cn

 

I am currently an Associate Professor in Tsinghua University. I received my Ph.D from HKUST in 2011, and B.E. from USTC in 2007. I used to spend 6 months in Prof. Aggelos K. Katsaggelos's lab in Northwestern University during the best season of Evanston in 2010, and I spent 8 months in Microsoft Research Asia (Beijing) with the host of Prof. Feng Wu in 2013. Later, I visited Prof. Eckehard Steinbach's group in Technical University of Munich (TUM) in 2014, supported by “Humboldt Research Fellowship for Experienced Researchers”.

Our team has always been interested in looking for practical problems and solutions. Along with understanding the real world using fancy computer vision techniques ("post-processing"), we believe that the innovation in imaging/sensing ("pre-processing") plays equally important role. Aiming for comprehensive, high-resolution, and realistic imaging/sensing of large-scale dynamic scenes, our work relates to Gigapixel Videography, Multi-Camera Array, Multiview 3D Reconstruction, 4D Lightfield Reconstruction etc., towards both the online hardware system and real-time algorithmic solutions.

News

*** If you are interested in working with us as a PostDoc or PhD / Master student, please contact us.

*** The PANDA dataset is available for downloading now!

  • February 5, 2021, one paper is accepted by IEEE TIP
  • January 22, 2021, one paper is accepted by Light: Science & Applications
  • January 7, 2021, one paper is accepted by Nature Photonics
  • December 2, 2020, one paper is accepted by IEEE TPAMI
  • October 8, 2020, one paper is accepted by Advances in Optics and Photonics
  • August 28, 2020, the 2nd Workshop (Challenge) on GigaVision was held in ECCV 2020
  • August 27, 2020, one paper is accepted by IEEE TPAMI
  • July 31, 2020, one paper ia accepted by Cell Patterns
  • July 29, 2020, one paper is accepted by ACM Multimedia 2020
  • July 3, 2020, one paper is accepted as ECCV 2020 Spotlight Paper
  • May 18, 2020, two papers are accepted by IEEE TPAMI
  • May 13, 2020, one paper is accepted by Nature Machine Intelligence
  • March 13, 2020, EventCap is accepted as CVPR 2020 Oral Paper
  • February 23, 2020, three papers are accepted by CVPR 2020
  • February 23, 2020, the PANDA dataset webpage is launched
  • February 21, 2020, one paper is accepted by ICCP 2020
  • June 17, 2019, the 1st Workshop on GigaVision in CVPR 2019

Selected Research Projects (Publication List)

Computational Photography

Visual Intelligence


Live Demo of PANDA dataset


Live Demo of OccuSeg


Live Demo of MultiscaleVR


Live Demo of EventCap

 

Augmenting Vascular Disease Diagnosis by Vasculature-aware Unsupervised Learning
Nature Machine Intelligence 2020

CrossNet++: Cross-scale Large-parallax Warping for Reference-based Super-resolution
TPAMI 2020

SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view Stereopsis
TPAMI 2020

Live Semantic 3D Perception for Immersive Augmented Reality
TVCG 2020

 

Multiscale-VR: Multiscale Gigapixel 3D Panoramic Videography for Virtual Reality
ICCP 2020 Oral

PANDA: A Gigapixel-level Human-centric Video Dataset
CVPR 2020

OccuSeg: Occupancy-aware 3D Instance Segmentation
CVPR 2020

EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera
CVPR 2020 Oral

 

Fourier-space Diffractive Deep Neural Network
PRL 2019

Gigapixel Video: A Cross Resolution Image Matching and Warping Approach
ICCP 2017 Oral

UnstructuredFusion: Realtime 4D Geometry and Texture Reconstruction using Commercial RGBD Cameras
TPAMI 2019

FlashFusion: Real-time Globally Consistent Dense 3D Reconstruction using CPU Computing
RSS 2018 Oral

Light Field Reconstruction Using Deep Convolutional Network on EPI and Extended Applications
TPAMI 2018

CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
ECCV 2018

Real-time Global Registration for Globally Consistent RGBD SLAM
TRO 2018

SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis
ICCV 2017