News & Activities
• Congratulation to our team (led by PhD student Liu
Liu, Liyuan Pan) for
winning the 3rd place at the
Google Landmark Challenge at CVPR 2018. There were over 100 teams worldwide
participated in the Challenge. The
novel technique that we developed can be used for robot (self-driving cars)
navigation and vehicle localisation.
• Express-of-interest: one 12 month
postdoctoral fellow position will be open at the ANU computer vision
group, working on 3D computer vision for autonomous vehicle
navigation. Contact me if you are
to start: 09-2018 or ASAP).
•A number of ACRV (ARC funded) Postdoctoral
fellow positions available at the ANU node, in all areas of computer vision, robotic vision, machine learning. (
The positions are already open on ANU website. application
due date: 30 August 2018)
•Invited talk at SSIST 2018, ShanghaiTech.
• Winning the prestigious Marr Prize Honourable Mention at
• Congratulations to Yifu and Laurent for winning the Best Student Paper Award at ICVS 2017.
•Congratulations to Suryansh et, al. for winning the Best Algorithm Award at the NRSFM-Challenge
at CVPR 2017 !
is doing intern at China’s Tencent AI
Research Lab in Shenzhen.
•Ami Drory has completed his PhD
study in applied computer vision for biomechanics and sports science.
• I will be serving the ACCV-2018
as a co- Program Chair. (Asian
Conference on Computer Vision 2018).
• I serve an Area Chair for ICCV 2017, Venice, Italy.
• My PhD student Mr. Joey Zhou is
visiting ETH, UZH (University of Zurich) until 2018, studying event camera based
visual SLAM, under the supervision of professor Davide
Scaramuzza - Robotics and Perception Group.
• Find an old photo:;-)
Laurent Kneip has joined Shanghai-Tech
University as a faculty member.
•Dr. Dingfu Zhou has completed his postdoc period at the ANU
and assumed a position at Baidu IDL, Beijing.
• Serve an Area Chair for ICCV
• Gao Zhu graduated with PhD degree
and joins DJI in Shenzhen.
graduated with a PhD degree in 2017 and now is a Postdoc with the Torr’s computer vision group at Oxford
• Deep Learning for Video based
Face Identification paper accepted by CVPR 2017.
• Deep learning for image matching
paper has been accepted to ECCV 2016.
• Ji Pan graduated and joins the
computer vision group of University of Adelaide.
•Our ANU vision group have 12
papers successfully accepted by the CVPR
2016 conference —a premier conference in international computer
vision research community.
• I serve on the Editorial Board
for IEEE T-PAMI.
Yang is visiting Harvard University as a visiting student.
Yang is doing an intern at Microsoft Research Asia in Beijing.
• Jointly with Dr Kim co-organise
the ACRA 2015 conference, a major annual event of Australia Robotics and
• Our monocular optical flow
algorithm has obtained the top rank on the KITTI and MPI Sintel (clean)
optical flow benchmark at the time of CVPR 2015 submission. Optical flow is a key algorithm for 3D
motion perception used in visual odometry for
vehicle navigation and self-driving (autonomous driving).
• A new postdoc position is open
until September 2015. The postdoc will work in the intersection of
Computer Vision and Plant Sciences within the collaboration between ARC
Centre of Excellence for Robotic Vision (ACRV, roboticvision.org), ARC
Centre of Excellence for Plant Energy Biology (CPEB,
plantenergy.uwa.edu.au), and the Australia Plant Phenomics Facility
• Welcome new Research Fellows
joining the ACRV (Australia ARC Centre for Robotic Vision)- ANU node, Dr. Anoop Cherian (formerly with LEAR,
INRIA, Grenoble,France), Dr. Basura Fernando (formerly with KU
Leuven,Belgium). We are also looking forward to welcoming two more
researchers to join the ANU CVR group, Dr. Ijaz Akhter (currently with MPI
Tuebingen, Germany) and Dr. DingFu (currently with UTC Paris, France).
• serve as an Area Chair for ICCV
2015 in the area of 3D Computer Vision and Structure-From-Motion.
• serve as Area Chair for BMVC
2015, Area Chair for 3DV (3DPVT) 2015, and TPC member for AVSS 2015.
• A short-term postdoc position is
available at the CVR group of ANU (partly funded by ARC). Details can be
found here in this PDF
file. Closing date: 1st May 2015.
• Congratulations to Dr Laurent Kneip who is
awarded an ARC DECRA Early Career Grant 2015-2017. We have 3 recent DECRA
Fellows with the ANU Computer Vision Group.
• Congratulations to
Yuchao for winning the DSTO Best Paper Award at
• Pan J, Yiran Z, Mathieu
S and Hongdong have won ICIP'14 Best Student Paper Award at the IEEE ICIP 2014 --the premier conference in IEEE
• Our Computer Vision group at ANU/NICTA have 12
papers accepted to ECCV 2014 Zurich.
Congratulations to ANU/NICTA vision group. We have 12 papers
accepted to CVPR’2014 — CVPR is one of the top conferences in computer
• serve IEEE CVPR-2015
Programme Committee as Area
Chair (in 3D Computer Vision). The conference will be
held in Boston 2015.
•Several new ACRV PhD Scholarships in computer
vision, robotics, machine learning, are available. Welcome top
students with strong research interests to apply.
•Four (4) ACRV Research Fellow positions are
available at the CVR group of ANU. Closing date: 7th July 2014.
• Five PhD Scholarships in robotics and computer
vision (machine learning) are available for the 2015 intake. ANU
application due date: 30th August 2014.
• Two FERL academic positions are available at the
Research School of Engineering of ANU. Closing date: September 2014. (see
ANU job site)
• Jointly with QUT (led
by professor Peter Corke, QUT), Monash, Adelaide,
as well as our very strong international partners (@ Oxford, ETH, ICL,
Georgia-Tech, INRIA, etc.), we have
succeeded in receiving major research funding ( $25 Millions AUD) from
ARC for building a Research Centre of Excellence.
• Congratulation to Dr Yuchao
Dai who wins an ARC DECRA - Early Career Award for 2014-2016.
• I am an Area
Chair for ECCV 2014 (3D vision), and an Area Chair for ICCV 2013 .
• Welcome new Research Fellow Dr Laurent Kneip (PhD 2012, RSL, ETH
Zurich) joining ANU computer vision and robotics group.
• We won an ARC Discovery Grant for 2013-2015,
jointly with Prof Hartley, Professor Phil Torr
(Oxford), and Prof Fredrik Kahl
(Lund). We will develop novel efficient methods for large scale
semantic labelling and annotation of images and videos.
• I am organizing (as one of the program co-chairs)
ICCV Workshop on CVAB, and ICCV Workshop on Big data in 3D Vision, Sydney
• I was a member of BVA (Bionic Vision Australia),
and an associate investigator for the ARC Australian Bionic Eyes Project
• Ten (10) papers accepted by CVPR 2013 (3 orals)
from authors of the ANU/NICTA Computer Vision group.
to Sadeep Jayasumana, Richard Hartley et al for winning the Canon Best Paper Award at DICTA 2013 Hobart.
to Worapan et al for winning the IEEE ICPR Best Student Paper
Award (biometric track) at ICPR 2010.
Visit ISRR Paris 6 University (UPMC). August-Sept,
to Yuchao, Mingyi for
winning the prestigious IEEE CVPR Best Paper
CVPR 2012 Rhode Island, Providence, for their work on Nonrigid
(deformable shape) structure-from-motion contributing to 3D computer
• Currently teaching
postgraduate/undergraduate ENGN4528/6528 Computer Vision, 2011, 2013,
2014, 2015 S1.
• Currently serving SRS convenor 2013, 2014.
• Teaching ENGN4627/6627 Intro to Robotics for
2010, 2011, 2012, and 2014.
• Visit University of Southern California, LA and
University Berkeley in 2010.
• Attend ICCV 2009 in Kyoto, Japan.
• Attend CVPR 2008 in Anchorage,
• Attend ICCV 2007 in Rio. Brazil
• Attend ECCV 2006 in Graz, Austria.
• Attend ICCV 2005 in Beijing, China.
• Attend ECCV 2004 in Prague,
I am a faculty member @ ANU
(Australian National University) and the Australia ARC Centre of Excellence for Robotic
Vision, where I do research in Computer Vision (3D Vision Reconstruction,
SFM and Robot SLAM), Image
Processing, and Machine Learning. Visiting RI, CMU, Carnegie Mellon
University, Pittsburgh, from 2017—March 2018.
I serve as
Associate Editor for IEEE-
Transaction on Pattern Analysis and Machine Intelligence (PAMI)—the No.1 journal in Computer Vision and
Artificial Intelligence, and Associate Editor for Image and Vision
Computing, etc. Program Co-Chair for DICTA
2017, ACCV 2018, ACRA 2015, and Area Chair for recent CVPR, ICCV, ECCV, BMVC, and
3DV. I contributed to the ARC-funded Australia’s Bionic Eye
Project (special initiative).
Prior to 2010 I was a Fellow with
the RSISE @ ANU and a Senior Research Scientist with
NICTA (National ICT Australia), Canberra
Labs. I am privileged to be
working under the mentoring of Professor Richard Hartley. Jointly with students and colleagues we
won a number of prestigious awards in Computer Vision research, including CVPR Best Paper Award, Marr Prize (Honourable Mention), IEEE-ICPR Best
Student Paper Award, IEEE ICIP Best
Student Paper Award, DSTO Best Paper Prize, DICTA CiSRA Best Paper Award at
ANU is the best
research university in Australia, located in the beautiful “Bush Capital”
City of Canberra. ANU has
multiple scholarship schemes available for PhD applicants. We also welcome students to apply to our ANU
Computer Vision PhD Program.
Current Research Projects
for 3D Visual Perception
Sensors for robust robotic vision (funded by ARC Centre of Excellence for
image based City-scale 3D modelling (funded by an ARC Discovery project).
Navigation for autonomous driving cars (self-driving cars, funded by a
global automobile manufacturer).
interaction for medical images (funded by Microsoft Research, via an ARC
and Motion Capture via subspace or sub-manifold clustering.
optimisation and inference for MRF/CRF.
neural networks and Deep Learning.
Optimisation in low level computer vision problems.
flying of autonomous robots in all-weather conditions.
Team (Current, and alumni):
Dr. Laurent Kneip (Now a tenure track professor of Shanghai Tech), ARC DECRA
Viorela Ila ( is
joining University of Sydney) , ACRV
Research Fellow; Dr. Anoop Cherian
ACRV Research Fellow; Dr. Yuchao Dai (now a Professor of NPU),
ARC DECRA Fellow; Dr. Dingfu
Zhou (Senior Researcher of BaiDu IDL), ANU Postdoctoral Fellow ;PhD students: ;Jiaolong Yang (Researcher of MSRC,
Microsoft-Research), Jie Liang, Mr.
Cristian Rodrigiuze, Joey Zhou, Mehdani M.,
Liu Liu, Yiran Zhong, Dylan Campbell, Pan Ji, Sadeep
Jayasumana,; Ajanthan Thalaiyasinga,Gao Zhu,Yansheng Ming, Mohammad Sadegh,Zhipeng
Xiao, Jae-hak Kim, Jun Sun, Gucan
The CVPR, ICCV and ECCV are premier conferences in
Computer Vision research community. The IEEE TPAMI,TIP, IJCV are top
journals in the field of computer vision, image and pattern recognition.
activity anticipation by predicting dynamic images,
ECCV workshop 2018
3D Reconstruction with a Stereo Event Camera,
Li, Davide Scaramuzza
Accepted by ECCV 2018
Computation for a Single Mixture Image,
Accepted by ECCV 2018
Stereo Video Matching with Deep RNN,
Accepted by ECCV 2018
Structure From Recurrent Motion: From Rigidity to Recurrency
Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian Perspective,Suryansh
Dai,Hongdong Li , In IEEE CVPR 2018
Ji Pan, Ian Reid,
et. al, Deep Kernel Subspace
Clustering for Multi-body Motion Segmentation, ICCV 2017 submission 4
Dylan C. et.
al. Globally-Optimal Inlier Set Maximisation for
Simultaneous Camera Pose and Feature Correspondence, ICCV 2017. ICCV Oral Presentation.
Suryansh, et. al. Monocular Dense 3D Reconstruction of a Complex
Dynamic Scene from Two Perspective Frames, ICCV 2017.
Liu Liu, et. A;, Efficient Global 2D-3D
Matching for Camera Localization in a Large-Scale 3D Map, ICCV 2017.
The 1st Winner of “Non-Rigid Structure from Motion
Challenge 2017” @ CVPR 2017
Suryansh and Dai, Yuchao
and Li, Hongdong. Spatial-temporal
union of subspaces for multi-body non-rigid structure-from-motion. Pattern Recognition, 2017.
Jiaolong Yang, Gang Hua, et al., Neural
Aggregation Networks for Video face Recognition, CVPR 2017
Gucan Long, Jose Alverue, Laurent Kneip,
Hongdong Li, et al, Learning image matching by watching a video, ECCV 2016
Yuchao Dai, Laurent Kneip, Hongdong Li,
Rolling Shutter Camera
IEEE CVPR 2016
Robust Optical Flow Estimation of
Double-Layer Images under Transparency or Reflection, IEEE CVPR 2016
Beyond Local Search:
Tracking Objects Everywhere with Instance-Specific Proposals, IEEE
Feature Tracker: A Segmentation-free Approach, IEEE CVPR 2016
Pan Ji, Mathieu
Salzmann, Hongdong Li,
Shape Interaction Matrix Revisited
and Robustified: Efficient Subspace Clustering
with Corrupted and Incomplete Data, IEEE ICCV 2015, Oral (3%
Training an artificial neural networks for image edge
detection, JZJU-Science, vol-2,
3D computer vision for ANU Self-Driving Car:
Visual odometry and vehicle ego-motion
estimation for autonomous driving using side-viewing multiple-camera rig, TR-ANU-CVRG,
Ajanthan Thalaiyasingam, R.
Hartley, M. Salzmann and H. Li, Iteratively
Reweighted Ishikawa Graph Cut for Multi-label MRFs with Non-convex
IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), Boston, MA, June 2015.
Jiaolong Yang, Hongdong Li,
Optical Flow Computation: the Piecewise Parametric Model Revisited.
IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), Boston, MA, June 2015. ( Code will be
method for multibody motion segmentation with unknown correspondences, in ECCV
Mathieu Salzmann, Hongdong Li:
dense subspace clustering.
WACV 2014: 461-468
Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li and
Multiple Manifold-valued Descriptors for Improved Object Recognition,
IEEE DICTA 2013, CiSRA"Best
Recognition Paper Award".
Yansheng Ming, Hongdong Li, Xuming He
Contour Cue and Region cue Salient Image Segmentation
(PDF coming soon..).
IEEE CVPR 2013 (poster).
< For more papers,
please see Publications
< Back to Top >