ECE PhD Candidate · Rice University

Hao Liang

Building 3D digital humans — fast, faithful avatars from a single photo with Gaussian Splatting & generative models.

Houston, TX · currently research intern @ Apple Digital Human
scroll
01 About
Practical systems that are simple, fast, fair & reliable.

I am an ECE PhD candidate at Rice University, advised by Prof. Guha Balakrishnan. Before Rice, I spent three wonderful years at Carnegie Mellon University, where I was fortunate to work closely with Prof. Gauri Joshi, Prof. Bhiksha Raj, and Prof. Giulia Fanti. I did my undergraduate studies at UESTC.

My research focuses on generative modeling, 3D human reconstruction, vision–language models, and federated learning. I like building practical systems that are simple, fast, fair, and reliable.

My research is supported by Samsung Research America. I am currently a research intern with the Apple Digital Human team.

Affiliation
Rice University — ECE
Advisor
Guha Balakrishnan
Currently
Research Intern, Apple Digital Human
Previously
CMU · Samsung Research America
02 Selected Work
3D faces & avatars, in the wild.
01

FastAvatar

Instant 3D Gaussian Splatting avatars from a single unconstrained pose — an encoder–decoder that predicts a full 3DGS head in ~3 seconds, ready for novel-view synthesis and real-time animation.
FastAvatar pipeline: encoder–decoder to 3DGS, novel view synthesis and real-time animation
02

SplatShot

3D face avatar generation from a single unconstrained photo — reconstructing per-person 3DGS avatars even from crowded, in-the-wild group shots.
SplatShot: single group photo input to multiple 3DGS avatar outputs
03

CelebA-3D

A large-scale, in-the-wild 3D face dataset — lifting single CelebA portraits into animatable 3DGS avatars at scale.
CelebA-3D input portrait Input · 2D portrait
Output · 3DGS avatar
03 Teaching
In the classroom.
Fall 2024
ELEC 566 — Introduction to Computer VisionRice University
Teaching Assistant
Spring 2022
ELEC 542 — Neural Methods for Image SynthesisRice University
Teaching Assistant
Fall 2019
11-785 — Introduction to Deep LearningCarnegie Mellon University
Teaching Assistant
04 Contact
Let's connect
hl106@rice.edu