Gaurav Shrivastava I am a PhD graduate from University of Maryland, College Park advised by Prof. Abhinav Shrivastava. My research focuses on the intersection of Machine Learning and Computer Vision. Specifically, my work encompasses Vision Language Models, Diffusion, Video Generation, Computational Photography, LLMs and Gaussian Process models. |
![]() |
![]() |
Efficient Continuous Video Flow Model for Video Prediction
PDF/ Project Page
Coming Soon! |
![]() |
Video Prediction by Modeling Videos as Continuous Multi-Dimensional Processes
PDF/ Project Page
click on the link! |
![]() |
Video Decomposition Prior: Editing Videos Layer by Layer
PDF / Project Page
Click on the link! |
![]() |
Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements |
![]() |
Hierarchical Video Prediction using Relational Layouts for Human-object Interactions |
![]() |
Diverse Video Generation using a Gaussian Process Trigger |
![]() |
Learning What Not to Model: Gaussian Process Regression with Negative Constraints
blog /
code /
project page /
PDF /
bibtex
Coming Soon! |