Welcome to my site

I currently work at Google Research.

Previouly I was a PhD student in College of Computing of Georgia Tech. I was co-advised by Jim Rehg and Frank Dellaert. My research interest lies in the intersection of the fields of computer vision, machine learning and robotics.

At Georgia Tech, I was affiliated with Computational Perception Laboratory (CPL), which comes under Center for Robotics and Intelligent Machines (RIM). Before that, I was at Robotics Research Lab of IIIT Hyderabad, India where I worked with Prof. K Madhava Krishna and Prof. C. V Jawahar.

My Publications Google Scholar

virtualMVFusion_thumbnail.gif Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru. Virtual Multi-view Fusion for 3D Semantic Segmentation. In ECCV 2020. Project Page pdf.gif vidMSsmall.jpg vidMSsmall.jpg

pillar_detection_eccv2020_thumbnail.png Yue Wang, Alireza Fathi, Abhijit Kundu, David Ross, Caroline Pantofaru, Thomas Funkhouser, Justin Solomon. Pillar-based Object Detection for Autonomous Driving. In ECCV 2020. pdf.gif vidMSsmall.jpg Code

lstm_detection_eccv2020_thumbnail.png Rui Huang, Wanyue Zhang, Thomas Funkhouser, Abhijit Kundu, Caroline Pantofaru, David A Ross, Alireza Fathi. An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds. In ECCV 2020. Project Page pdf.gif vidMSsmall.jpg vidMSsmall.jpg

ato_thumbnail.png Jingwei Huang, Justus Thies, Angela Dai, Abhijit Kundu, Chiyu Max Jiang, Leonidas Guibas, Matthias Nießner, Thomas Funkhouser. Adversarial Texture Optimization from RGB-D Scans. In CVPR 2020. Project Page pdf.gif vidMSsmall.jpg Code

dops_thumbnail.png Mahyar Najibi, Guangda Lai, Abhijit Kundu, Zhichao Lu, Vivek Rathod, Thomas Funkhouser, Caroline Pantofaru, David Ross, Larry S Davis, Alireza Fathi DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes. In CVPR 2020. pdf.gif vidMSsmall.jpg

3drcnn_thumbnail.jpg Abhijit Kundu, Yin Li, and James M. Rehg. 3D-RCNN: Instance-level 3D Object Reconstruction via Render-and-Compare​. In CVPR 2018. ( Oral) Project Page pdf.gif Code

fso_thumb_a.jpg Abhijit Kundu, Vibhav Vineet, and Vladlen Koltun. Feature Space Optimization for Semantic Video Segmentation. In CVPR 2016. ( Oral ) Project Page pdf.gif bibtex.gif vidMSsmall.jpg Code

eccv14-thumb.jpgAbhijit Kundu, Yin Li, Frank Dellaert Fuxin Li and James M. Rehg. Joint Semantic Segmentation and 3D Reconstruction from Monocular Video. In ECCV 2014. Project Page pdf.gif bibtex.gif vidMSsmall.jpg

multiscale_planning.gifFlorian Hauer, Abhijit Kundu, James M. Rehg and Panagiotis Tsiotras. Multi-scale perception and path planning on probabilistic obstacle maps. In ICRA 2015. Paper: pdf.gif bibtex.gif

modern_map_fg.svgVikas Dhiman, Abhijit Kundu, Frank Dellaert and Jason J. Corso. Modern MAP inference methods for accurate and fast occupancy grid mapping on higher order factor graphs. In ICRA 2014. pdf.gif bibtex.gif

vers-full-thumb.jpg Abhijit Kundu, K M. Krishna and C. V. Jawahar. Realtime Multibody Visual SLAM with a Smoothly Moving Monocular Camera. In ICCV 2011. (Oral ) pdf.gif bibtex.gif pdf.gif vidMSsmall.jpg

icra2012thumbnail.jpg Rahul Namdev, Abhijit Kundu, K M. Krishna and C. V.Jawahar. Motion Segmentation of Multiple Objects from a Freely Moving Monocular Camera. In ICRA 2012. pdf.gif bibtex.gif vidMSsmall.jpg

ICVGIPoverview.jpg Abhijit Kundu, K M. Krishna and C. V.Jawahar. Realtime Motion Segmentation based Multibody Visual SLAM. In ICVGIP 2010. Oral (<10%) ( Best Paper Award). pdf.gif bibtex.gif

iros2009logo.jpg Abhijit Kundu, K M. Krishna and J. Sivaswamy. Moving Object Detection by Multi-View Geometric Techniques from a Single Camera Mounted Robot. In IROS 2009. pdf.gif bibtex.gif vidMSsmall.jpg

robio10ovb.jpg Abhijit Kundu, C. V.Jawahar and K M. Krishna. Realtime Moving Object Detection from a Freely moving Monocular Camera. In ROBIO 2010. pdf.gif