Email: MMESHRY [AT] CS [DOT] UMD [DOT] EDU
I'm a PhD candidate at the Perception and Intelligence Lab at the University of Maryland, College Park.
I'm advised by Larry Davis and Abhinav Shrivastava.
I'm interested in generative modeling, image synthesis and neural rendering.
My research focuses on improving the training of mulit-modal image translation networks, as well as applying image-to-image translation and neural rendering techniques for the task of novel view synthesis.
Learned Spatial Representations for Few-shot Talking-Head Synthesis
StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis
Neural Rerendering in the Wild
Two Stream Self-Supervised Learning for Action Recognition
Texture Synthesis with Recurrent Variational Auto-Encoder
Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets
Multi-Modality Feature Transform: An Interactive Image Segmentation Approach
A scalable maximum-clique algorithm using Apache Spark
Amr Elmasry, Ayman Khalafallah, Moustafa Meshry
Few-shot Synthesis of Talking Heads - [UNDER REVIEW, 2020].
Neural rerendering from 3D models. U.S. Patent Application 16/837,612, filed October 8, 2020.
Honours and Awards
- Best paper award finalist at the Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (top 1% of submissions).
- University of Maryland Graduate School Deans Fellowship, 2016 and 2017
- EducationUSA Opportunity Fund: Support from the America-Mideast Educational and Training Services Inc. is awarded to highly qualified students to study in the US.
- ranked 4th at the ACM Egyptian Collegiate Programming Contest 2011, (ECPC’11).
- ranked 19th at Google Code Jam Africa, 2011.