Zhicheng Geng
Applied Scientist
Amazon
Biography
Zhicheng Geng is an Applied Scientist at Amazon Machine Learning Solutions Lab. He received his Ph.D. degree in Geophysics from Jackson School of Geoscience, The University of Texas at Austin in 2022, advised by Prof. Sergey Fomel. Before that, he obtained his B.S. degree from Tongji University in 2017.
His research focuses on computer vision and deep learning. He is also a main contributor of Madagascar, a package for reproducible geophysical data processing.
Interests
- Computer Vision
- Deep Learning
- Generative AI
Education
-
PhD in Geophysics, 2022
The University of Texas at Austin
-
BSc in Geophysics, 2017
Tongji University
Experience
Applied Scientist
Amazon
Research Intern
Microsoft
- Spatial temporal interpolation for smooth video conference experience via limited-computation transformer.
- Achieved SOTA performance with smaller number of parameters, smaller memory consumption and higher FPS.
- Submissions to top conference and patent applications in preparation.
Research Intern
Microsoft
- Extremely lightweight model based on deformable convolutions for real-time RAW image denoising as an online camerasensor driver alternative.
- Knowledge transferred to the production team for the next generation surface and Windows
Recent Publications
Quickly discover relevant content by filtering publications.
(2022).
Semisupervised salt segmentation using mean teacher.
Interpretation.
(2021).
Deep relative geologic time: a deep learning method for simultaneously interpreting 3-D seismic horizons and faults.
Journal of Geophysical Research: Solid Earth.
(2020).
Building realistic structure models to train convolutional neural networks for seismic structural interpretation.
Geophysics.
(2020).
Deep learning for relative geologic time and seismic horizons.
Geophysics.
(2020).
Relative time seislet transform.
Geophysics.
Contact
- 10611 Exploration Way, Austin, TX 78759