Krishna Regmi, Ph.D. is a senior R&D engineer on Kitware’s Computer Vision Team located in Carrboro, North Carolina. Krishna is involved in projects that involve satellite imagery analytics, for example, object detection in satellite imagery with low-shot learning.
Prior to joining Kitware, Krishna was a graduate research and teaching assistant at the University of Central Florida. His research focused on using Generative Adversarial Networks (GANs) to generate images and videos from novel views as well as on image matching and video geolocalization. His work on cross-view image synthesis published at the Conference on Computer Vision and Pattern Recognition (CVPR) in 2018 introduced a novel computer vision problem to the research community.
While working on his Ph.D., Krishna led the National Geo-Spatial Agency (NGA) research project on image and video geolocalization. He developed a novel solution to cross-view image matching by leveraging generative models to synthesize cross-view images to bridge the domain gap between query ground and gallery aerial images. He was also a research scientist intern for Netflix where he worked on frame deblurring for the application of Personalized Artwork Creation.
Before earning his master’s degree, Krishna was a lecturer at the Kantipur Engineering College, Tribhuvan University, Nepal where he taught different undergraduate level courses.
Krishna received his Ph.D. in computer science from the University of Central Florida in 2021. In 2015, he received his master’s degree in electrical engineering from Southern Illinois University Edwardsville. Krishna received his bachelor’s degree in electrical and communication engineering from Tribhuvan University in Nepal in 2009 and he was a visiting undergraduate student at the University of Bradford from 2009-2010.
ORC Doctoral Fellowship presented by the University of Central Florida, 2016-2017
Competitive Graduate Award presented by Southern Illinois University Edwardsville, 2013-2014
Invited Talks & Media
Invited Talk, Bridging the Domain Gap for Ground-to-Aerial Image Matching, Moving Cameras Workshop, International Conference on Computer Vision (ICCV), 2019
Professional Associations & Service
Reviewer for the Winter Conference on Applications of Computer Vision (WACV), 2020-present
Reviewer for the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020-present
Reviewer for the Journal of Big Data, 2020-present
- S. Shiraz, K. Regmi, S. Vyas, Y. Rawat, and M. Shah, "Novel View Video Prediction using a Dual Representation," in 2021 IEEE International Conference on Image Processing (ICIP), 2021. [URL]
- K. Regmi and M. Shah, "Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing," in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021. [URL]
- K. Regmi and A. Borji, "Cross-view image synthesis using geometry-guided conditional GANs," Computer Vision and Image Understanding, vol. 187, pp. 102788, Oct. 2019. [URL]
- K. Regmi and M. Shah, "Bridging the Domain Gap for Ground-to-Aerial Image Matching," in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019. [URL]
- K. Regmi and A. Borji, "Cross-View Image Synthesis Using Conditional GANs," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. [URL]