Nikhil Makkar

Life Update: Moved back to India and building Auric AI Labs.

I am a PhD student at Purdue University. My research interests broadly focus on computer vision, including 3D reconstruction using learning-based 3D deep models, large scale spatiotemporal data analysis, remote sensing and GeoAI.

Before starting PhD I worked with Dr. Lexie Yang and Dr. Dalton Lunga in GeoAI at Oak Ridge National Laboratory

Research

H. L. Yang, N. Makkar, M. Laverdiere, and A. Rose, "Boundary-aware adversarial learning domain adaption and active learning for cross-sensor building extraction", IEEE Journal of Selected Topics in Earth Observations and Remote Sensing, 2024.

paper

N. Makkar, H. L. Yang, and S. Prasad, "Adversarial learning based discriminative domain adaptation for geospatial image analysis", IEEE Journal of Selected Topics in Earth Observations and Remote Sensing, 2021.

paper

N. Makkar and H. L. Yang, "Entropy and boundary based adversarial learning for large scale unsupervised domain adaptation", in IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, IEEE, 2020

paper

D. Lunga, R. Dhamdhere, S. Walters, L. Bragg, N. Makkar, and M. Urban, "Learning to count grave sites for cemetery observation models with satellite imagery", IEEE Geoscience and Remote Sensing Letters, 2020.

paper

X. Deng, H. L. Yang, N. Makkar, and D. Lunga, "Large scale unsupervised domain adaptation of segmentation networks with adversarial learning", in IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, IEEE, 2019.

paper

Projects

Digital Surface Model (DSM) Generation Using Conditional Diffusion (2024).

Blog, Code

Point Cloud Classification in Wild (2024).

Blog

An Interactive Visualization of the Ruins of Machu Llacta using VTK and PyQt6 (2023).

Video, Code

Creating 3D Scenes From 2D Images Using Shaders (2022).

Presentation, Code

Impact of Transfer Learning in Extreme Change of Modality - Detecting Cancer Using CNNs (2017).

Article