Abhishek Kar
a...@cs.berkeley.edu

I am a graduate student in Jitendra Malik's group at UC Berkeley working on 3D Computer Vision. Before moving to Berkeley, I completed my undergrad at IIT Kanpur where I worked with Prof. Amitabha Mukerjee and Dr. Sumit Gulwani on computer vision and intelligent tutoring systems. My website from those days can be found here. I have also spent time at Microsoft Research working on viewing large imagery on mobile devices.

Email | CV | Google Scholar | LinkedIn | Facebook

Publications

I'm interested in 3D computer vision - more specifically inferring 3D shape from image collections in the wild.

basisshapes

Category-Specific Object Reconstruction from a Single Image
Abhishek Kar*, Shubham Tulsiani*,João Carreira, Jitendra Malik
arXiv preprint, 2014

abstract | bibtex | supplemental | videos | arxiv

Object reconstruction from a single image -- in the wild -- is a problem where we can make progress and get meaningful results today. This is the main message of this paper, which introduces the first fully automatic pipeline having pixels as inputs and dense 3D surfaces of various rigid categories as outputs in images of realistic scenes. At the core of our approach are novel deformable 3D models that can be learned from 2D annotations available in existing object detection datasets, that can be driven by noisy automatic object segmentations and which we complement with a bottom-up module for recovering high-frequency shape details. We perform a comprehensive quantitative analysis and ablation study of our approach using the recently introduced PASCAL 3D+ dataset and show very encouraging automatic reconstructions on PASCAL VOC.

@inproceedings{categoryshapes14,
  Author = {Abhishek Kar and 
  Shubham Tulsiani and 
  Joao Carreira and 
  Jitendra Malik},      
  Title  = {Category-Specific Object Reconstruction
  from a Single Image},
  Booktitle = {arXiv preprint arXiv:1411.6069},
  Year  = {2014}}
                

Virtual View Networks for Object Reconstruction
João Carreira, Abhishek Kar, Shubham Tulsiani, Jitendra Malik
arXiv preprint, 2014

abstract | bibtex | videos | arxiv

All that structure from motion algorithms “see” are sets of 2D points. We show that these impoverished views of the world can be faked for the purpose of reconstructing objects in challenging settings, such as from a single image, or from a few ones far apart, by recognizing the object and getting help from a collection of images of other objects from the same class. We synthesize virtual views by com- puting geodesics on novel networks connecting objects with similar viewpoints, and introduce techniques to increase the specificity and robustness of factorization-based object reconstruction in this setting. We report accurate object shape reconstruction from a single image on challenging PASCAL VOC data, which suggests that the current domain of appli- cations of rigid structure-from-motion techniques may be significantly extended.

@inproceedings{vvn14,
  Author = {Joao Carreira and 
  Abhishek Kar and 
  Shubham Tulsiani and 
  Jitendra Malik},      
  Title  = {Virtual View Networks for 
  Object Reconstruction},
  Booktitle = {arXiv preprint arXiv:1411.6091},
  Year  = {2014}}
                

Looking At You: Fused Gyro and Face Tracking for Viewing Large Imagery on Mobile Devices
Neel Joshi, Abhishek Kar, Michael F. Cohen
ACM SIGCHI Conference on Human Factors in Computing Systems (CHI), 2012

abstract | bibtex | website | video

We present a touch-free interface for viewing large imagery on mobile devices. In particular, we focus on viewing paradigms for 360 degree panoramas, parallax image sequences, and long multi-perspective panoramas. We describe a sensor fusion methodology that combines face tracking using a front-facing camera with gyroscope data to produce a robust signal that defines the viewer's 3D position relative to the display. The gyroscopic data provides both low-latency feedback and allows extrapolation of the face position beyond the the field-of-view of the front-facing camera. We also demonstrate a hybrid position and rate control that uses the viewer's 3D position to drive exploration of very large image spaces. We report on the efficacy of the hybrid control vs. position only control through a user study.

@inproceedings{joshi2012looking,
title={Looking at you: fused gyro and face
tracking for viewing large imagery on mobile devices},
author={Joshi, Neel and Kar, Abhishek and Cohen, Michael},
booktitle={Proceedings of the SIGCHI Conference
on Human Factors in Computing Systems},
pages={2211--2220},
year={2012},
organization={ACM}
}
                

Other Projects

Chemistry Studio: An Intelligent Tutoring System for the Periodic Table
Abhishek Kar*, Ankit Kumar*, Sumit Gulwani, Ashish Tiwari, Amey Karkare
Undergraduate Thesis, IIT Kanpur, 2012

slides | talk 1 | talk 2

Teaching

pacman

CS189: Introduction to Machine Learning - Spring 2013 (GSI)
Instructor: Prof. Jitendra Malik
Awarded the Outstanding GSI Award

CS188: Introduction to Artificial Intelligence - Spring 2014 (GSI)
Instructor: Prof. Pieter Abbeel


this guy's website is awesome