Avatar

Ph.D Candidate

Department of Computer Science
          The University of Georgia
          415 Boyd Grad Studies Research Center
          Athens, GA, 30605-7404

aruncs [AT] uga.edu
          arunkarthikcs [AT] gmail.com

+1 (706) 20SIX-ONE4FIVE4

Resume

qr

   












































ARUN, CS KUMAR

I am Arun, a Ph.D candidate in Computer Science at the University of Georgia, under the supervision of Dr. Suchendra M. Bhandarkar and Dr. Mukta Prasad (co-advised). My research is primarily focused on 3D Computer Vision, specifically on Single view 3D reconstruction, 3D Shape Modelling and Structure-from-Motion/SLAM problems.

Publications (peer reviewed)

    Primary 

  • Monocular Depth Prediction using Generative Adversarial Networks,
    In Proc. IEEE Computer Vision and Pattern Recognition (CVPR) 2018 Workshop on Deep Learning for Visual SLAM
    Arun CS Kumar, Suchendra M. Bhandarkar, Mukta Prasad

  • DepthNet: A Recurrent Neural Network Architecture for Monocular Depth Prediction,
    In Proc. IEEE Computer Vision and Pattern Recognition (CVPR) 2018 Workshop on Deep Learning for Visual SLAM
    Arun CS Kumar, Suchendra M. Bhandarkar, Mukta Prasad

  • Learning Hierarchical Models for Class-Specific Reconstruction from Natural Data,
    In Proc. IEEE Computer Vision and Pattern Recognition (CVPR) 2018 Workshop on Autonomous Driving
    Arun CS Kumar, Suchendra M. Bhandarkar, Mukta Prasad

  • Matching Disparate Image Pairs using Shape-Aware ConvNets,
    In Proc. IEEE Winter Conference on Applications of Computer Vision (WACV), 2019
    Shefali Srivastava*, Abhimanyu Chopra*, Arun CS Kumar, Suchendra M. Bhandarkar, Deepak Sharma (*-equal contribution)

  • Deep Spectral Correspondence for Matching Disparate Image Pairs,
    Under Review for Computer Vision and Image Understanding (CVIU) Journal 2018
    Arun CS Kumar*, Shefali Srivastava*, Anirban Mukhopadhyay, Suchendra M. Bhandarkar(*-equal contribution)

  • Class-specific Object Pose Estimation and Reconstruction using 3D Part Geometry,
    In Proc. European Conference on Computer Vision (ECCV) 2016 Workshop on Geometry Meets Deep Learning
    Arun CS Kumar, Andras Bodis-Szomuru, Suchendra M. Bhandarkar, Mukta Prasad

  • Joint Geometric Graph Embedding for Partial Shape Matching in Images,
    In Proc. IEEE Winter Conference on Applications of Computer Vision (WACV), 2016
    Arun CS Kumar*, Anirban Mukhopadhyay*, Suchendra M. Bhandarkar (*-indicates equal contribution)

    • Others 

  • Guessing Objects in Context, In SIGGRAPH 2016 (poster)
    Karan Sharma, Arun CS Kumar, Suchendra M. Bhandarkar

  • A Deep Learning Paradigm for Detection of Harmful Algal Blooms,
    In Proc. IEEE Winter Conference on Applications of Computer Vision (WACV) 2017
    Arun CS Kumar, Suchendra M. Bhandarkar

  • Automated Image Captioning using Nearest Neighbors Approach driven by top-object Detections,
    In International Joint Conference on Neural Networks workshops (IJCNN-W) 2017
    Karan Sharma, Arun CS Kumar, Suchendra M. Bhandarkar

  • Action Recognition in Still Images Using Word Embeddings from Natural Language Descriptions,
    In Proc. IEEE Workshops on Applications of Computer Vision (WACV) 2017
    Karan Sharma, Arun CS Kumar, Suchendra M. Bhandarkar

Other Publications & Presentations 

  • Towards Geometry-aware Deep Learning Models for Single-view 3D Reconstruction,
    Doctoral Consortium, Computer Vision and Pattern Recognition (CVPR) 2018, Arun CS Kumar

  • Class-Specific Object Pose Estimation and Shape Recovery,
    In the Ph.D Forum, IEEE Winter Conference on Applications of Computer Vision (WACV) 2017, Arun CS Kumar

  • Determining Degree of Coincidence between different Historical Events using Satellite Imagery,
    In 9th SoFor GIS Conference, 2013, Arun CS Kumar, Chris J. Cieszewski