UMAR IQBAL
  • Home
  • Publications
  • Contact

Hi, Welcome to my homepage!!!

Picture
I am a Senior Research Scientist at NVIDIA Research and part of the Machine Learning and Perception group headed by Jan Kautz. Prior to that, I completed my PhD in Computer Science (2014-2018) from the University of Bonn, Germany, under the supervision of Prof. Juergen Gall. I completed my M.Sc. degree in Information Technology (2011-2013) with majors in Image and Video Signal Processing from Tampere University of Technology (TUT), Finland. Alongside, I also worked at Nokia Research Center as an External Computer Vision Researcher. I completed my B.Sc. degree in Computer Engineering from COMSATS Institute of Information Technology, Pakistan, and later also worked there as a Research Associate at the Computer Vision Research Group during 2010-2011. 

​
Research Interests: 
Computer Vision, Computer Graphics, Deep Learning,  Digital Humans, 3D Scene Understanding 


News!

04/10/2021: One paper accepted to 3DV. 
23/07/2021: Two papers accepted to ICCV'21. 
10/07/2021: I am serving as an Area Chair for BMVC'21. 
24/02/2020: Two papers accepted to CVPR'20. One on weakly-supervised 3D human pose estimation and the other on self-supervised viewpoint learning. More info to follow. 
22/07/2019: A paper on few-show adaptive gaze estimation has been accepted to ICCV'19. Code coming soon! 
05/07/2019: My dissertation has won the DAGM MVTec Dissertation Award 2019. DAGM (German Association for Pattern Recognition) represents the German community for pattern recognition including computer vision and machine learning. 
14/01/2019: I have joined Jan Kautz's lab at Nvidia Research as a post-doctoral Research Scientist. 
30/11/2018: Successfully defended my PhD with the highest possible distinction (summa cum laude).
09/09/2018: Received the Best Poster Award for our work on hand pose estimation at the 4th International Workshop on Observing and Understanding Hands in Actions (HANDS), 2018
03/07/2018: Our work on 2D and 3D hand pose estimation is accepted to ECCV 2018.
03/07/2018: JointFlow paper on multi-person pose tracking is accepted to BMVC-2018. 
12/05/2018: JointFlow paper on multi-person pose tracking is available online. 
25/04/2018: A paper on 2D and 3D hand pose estimation from RGB images is available on ArXiv.
30/03/2018: We are organizing 2nd PoseTrack Challenge and Workshop in conjunction with ECCV-2018 in Munich. Stay tuned at http://www.posetrack.net for more info!!
30/09/2017: I will spend next six months as Research Intern in Jan Kautz's lab at Nvidia Research.  
26/09/2017: Evaluation server for PoseTrack challenge is now open. All the best to all participants.   
10/07/2017: Pre-release of PoseTrack dataset is available now. Grab your copy here.
15/06/2017: Webpage for PoseTrack Challenge is down as we are moving our website to a new server. Apologies for the downtime. Will be accessible again soon.
08/05/2017: The extended version of our CVPR-2016 paper on 3D human pose estimation is available. [arXiv]. 
05/04/2017: Webpage for PoseTrack Challenge is up!
31/03/2017: We are organizing the PoseTrack Challenge on Human Pose Estimation and Tracking in the Wild at ICCV-2017. Stay tuned at http://www.posetrack.net for more info!!
​
26/02/2017: Our paper on Multi-Person Pose Estimation and Tracking accepted to CVPR-2017,  arXiv.  Source code, models, and dataset coming Soon... 
23/01/2017: Our paper on action conditioned human pose estimation accepted to FG-2017, arXiv. Project Page (Coming Soon). 
29/11/2016: A paper on multi-person pose tracking is available on arXiv. Project Page. 
24/08/2016: A paper on multi-person human pose estimation accepted to ECCV, Workshop on Crowd Understanding, 2016. Project Page.
14/03/2016: A paper on action conditioned human pose estimation is available on arXiv.
02/03/2016: A paper on 3D human pose estimation accepted to CVPR 2016! Project page is up.
05/02/2014: Starting doctoral studies at the Computer Vision Research Group (Prof. Dr. Juergen Gall), University of Bonn, Germany

Other Information

 Resume






Powered by Create your own unique website with customizable templates.
  • Home
  • Publications
  • Contact