Mehar Khurana

I'm currently completing my undergrad at IIIT Delhi, where I'm working with Prof. Saket Anand and Depanshu Sani on Active Learning in Animal Re-Identification.

Previously, I was a research intern at the Toronto Computation Imaging Group (TCIG), where I worked with Prof. David Lindell and Anagh Malik on multi-view reconstruction using single-photon images, and curated a single-photon dataset.

I have also worked with Prof. Deva Ramanan, Prof. James Hays and Neehar Peri on cross-modal pre-training for 3D object detection.

Email  /  CV  /  Scholar  /  GitHub

Research

I am interested in the fields of computer vision, computational imaging, deep learning, and generative AI. My research primarily focuses on understanding, interpreting and reconstructing the physical world.

Pre-training on pseudolabels generated by 2D foundation models significantly improves 3D object detection accuracy with limited labeled data for both LiDAR-only and multi-modal detectors.

Source code stolen from Jon Barron's website.