Zhengming Yu

I received my bachelor degree from South China University of Technology(SCUT) in Guangzhou, majoring in automation. I am now an incoming CS Ph.D. student of Texas A&M University, supervised by Prof. Wenping Wang. My research interests include 3D vision, computer graphics and generative model.

I spent a wonderful time in XR-Lab of SenseTime Research as a research intern supervised by Dr. Wayne Wu and Dr. Kwan-Yee Lin, where I worked on neural rendering, digital human, and audio driven generative model.

I am always open to discussing with different people. Feel free to drop me an email if you are interested! :)

Email  /  Github  /  Linkedin

profile photo
Research & Project
MonoHuman: Animatable Human Neural Field from Monocular Video
Zhengming Yu, Wei Cheng, Xian Liu, Wayne Wu, Kwan-Yee Lin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Paper / Project / Code

A novel method to model digital human body using neural implicit representation to achieve novel view synthesis and animation.

OpenXRNeRF GitHub Repo stars
Open source project, 2022
project page

Role: main contributor. XRNeRF is an open-source PyTorch-based codebase for Neural Radiance Field (NeRF).

OpenXDLab - Renbody
Open source dataset, 2022
project page

Role: main contributor. Rendbody dataset is the largest open source human performance dataset with multiple ultra-high-resolution cameras capturing fine details of human pose, clothing, and motion.

Question Answering System
product

Role: Algorithm developer. Develop the question answering nlp algorithm that can understand and answer the questions from customer.

Audio Driven Co-speech Gesture Generation
code

Multi modal generation: using speech audio and text to generate correspondent gesture.

Selected Honors & Awards

National Scholarship. 2019, 2020

Alibaba TianChi Competition Top 1.2%. 2021

Misc

šŸ€Basketball. I love basketball, though the team i am in always won a second place:)

šŸ§—Rock Climbing. V2 player now and still improving.

šŸŽKarting Racing. Always step on the accelerator, no brake when cornering.


Template credits: Jon Barron