bio photo

PhD student at Visual Learning Lab HCI, Univ. Heidelberg

Email Facebook LinkedIn Scholar

I am a PhD student with Prof. Carsten Rother at Visual Learning Lab (University of Heidelberg) and co-advised by Prof. Andreas Geiger.
I focus on developing algorithms and data for semi/self-supervised learning of computer vision tasks.
I did my Master’s at Robotics Research Center, IIIT-Hyderabad with Prof. K Madhava Krishna, where I worked on object search in indoor environments.

Email : siva.mustikovela@iwr.uni-heidelberg.de


News
  • Our work on self-supervised viewpoint learning from image collections is accepted at CVPR 20
  • Interned at NVIDIA Research from May - November 2019
  • 2 papers accepted at ACCV 18, instance aware 6D object pose estimation [pdf] and geometry aware realistic image synthesis[pdf]
  • Our work on exploring recognition granularities to improve object scene flow estimation is accepted at ICCV 17 [pdf]
  • Our work on efficient data augmentation with synthetic objects to train CNNs is accepted in IJCV 18 [pdf]
  • Our work on photo-realistic augmentation of images with synthetic objects to train CNNs is accepted at BMVC 17 [pdf]

Publications

Self-Supervised Viewpoint Learning From Image Collections
Siva Karthik M, Varun Jampani , Shalini De Mello , Sifei Liu , Umar Iqbal , Carsten Rother, Jan Kautz
CVPR 20 [Paper] [Project] [Code]  
iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects
Siva Karthik M*, Omid Hosseini Jafari*, Karl Pertsch, Eric Brachmann, Carsten Rother
ACCV 18 [Paper]   *equal contribution
Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?
Siva Karthik M*, Aseem Behl*, Omid Hosseini Jafari*, Hassan Abu Alhaija, Carsten Rother, Andreas Geiger
ICCV 17 [Paper]   *equal contribution
Geometric Image Synthesis
Hassan Abu Alhaija, Siva Karthik M, Andreas Geiger, Carsten Rother
ACCV 18 [Paper] [video]  
Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes
Hassan Abu Alhaija, Siva Karthik M, Lars Mescheder, Andreas Geiger, Carsten Rother
IJCV 18 [Paper]
Augmented Reality Meets Deep Learning for Car Instance Segmentation in Urban Scenes
Hassan Abu Alhaija, Siva Karthik M, Lars Mescheder, Andreas Geiger, Carsten Rother
BMVC 17 [Paper]
Can Ground Truth Label Propagation from Video help Semantic Segmentation?
Siva Karthik M, Michael Yang, Carsten Rother
Video Seg. Workshop, ECCV 16 [Paper]
Markov Random Field based Small Obstacle Discovery over Images
Siva Karthik M*, Suryansh Kumar*, K Madhava Krishna
ICRA 14 [Paper] *equal contribution
Guess from Far, Recognize when Near: Searching Floor for Small Objects
Siva Karthik M, Sudhanshu Mittal, K Madhava Krishna
ICVGIP 14 [Paper] [video]

I am privileged to be associated with the following
PhDBachelor's & Master'sIntern InternIntern