Ang Cao

I am a third-year Ph.D. student (2020-) in Computer Science and Engineering (CSE) at the University of Michigan, Ann Arbor, supervised by Prof. Justin Johnson. My research interests lie in the field of Computer Vision and Machine Learning.

I got my M.S. degree(2018-2020) at the University of Michigan, majoring in Signal & Image Processing and Machine Learning in ECE. My Bachelor's degree (2014-2018) was received from the School of Electronic Information at Wuhan University in China.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
Research

* indicates joint authorship

Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
Lukas Höllein *, Ang Cao *, Andrew Owens, Justin Johnson, Matthias Nießner
arXiv, 2023
project page/ arXvi/ video/ code

We generate meshes of full 3D rooms using text-to-image models.

HexPlane: A Fast Representation for Dynamic Scenes
Ang Cao, Justin Johnson
CVPR, 2023
project page/ arXvi/ video/ code

An elegant representation for dynamic 3D scenes using six feature planes.

FWD: Real-time Novel View Synthesis with Forward Warping and Depth
Ang Cao, Chris Rockwell, Justin Johnson
CVPR, 2022
project page / arXiv / video / code /

A generalizable novel view synthesis method with sparse inputs, which gives high-quality synthesis in real-time.

Inverting and Understanding Object Detectors
Ang Cao, Justin Johnson
Tech report, 2021
arXiv / code /

Revealing intriguing properties of detectors by applying our layout inversion technique.

Unified Signal Compression Using Generative Adverserial Networks
Bowen Liu *, Ang Cao * , Hun-Seok Kim
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Oral, 2020
arXiv / code /

Proposing an ADMM (alternating direction method of multipliers) to compress the signal into quantized latent vectors.


Huge thanks to Jon Barron for the awesome template.