Abhijit Kundu

prof_pic.jpg

Passionate about advancing the frontiers of computer vision, machine learning, and robotics.

I currently work at Google DeepMind. Previously I was with the Perception team at Google Research.

I finished my PhD in Computer Science from Georgia Tech. At Georgia Tech, I was co-advised by Jim Rehg and Frank Dellaert. 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.

news

Jul 11, 2024 :book: We released OmniNOCS a new large unified NOCS dataset. To appear at ECCV 2024.
Mar 1, 2024 :book: Two new papers: NeRFMeshing to appear at 3DV 2024 and NIFTY to appear at CVPR 2024.
Dec 1, 2023 :earth_americas: Google Maps now has immersive views for routes. See how they work via this blog post.
Apr 1, 2022 :book: Two papers Panoptic Neural Fields and Kubric accepted at CVPR 2022.
May 29, 2021 :earth_americas: Some of our work with Google Maps were announced at Google I/O.

selected publications

  1. Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation
    In CVPR 2022
  2. Virtual Multi-view Fusion for 3D Semantic Segmentation
    In ECCV 2020
  3. 3D-RCNN: Instance-level 3D Object Reconstruction via Render-and-Compare
    In CVPR 2018
  4. Feature Space Optimization for Semantic Video Segmentation
    In CVPR 2016
  5. Joint Semantic Segmentation and 3D Reconstruction from Monocular Video
    In ECCV 2014