Shichao (Nicholas) Li
李世超

I am currently a research engineer at DJI automotive working on perception. I obtained my Ph.D. degree from the CSE department of HKUST, where I was advised by Prof. Kwang-Ting Cheng and have also worked with Prof. Chi-Keung Tang. Before that, I received my B. E. degree from ZJU.

My general research interests are computer vision and machine learning. Specifically, I'm interested in the representation, processing, and simulation of 3D data/models, its reconstruction/inference from a set of 2D projections, as well as its applications in autonomous perception and AR/VR.

Email  /  CV  /  Google Scholar  /  Linkedin  /  Github

profile photo
Research

The following is a list of my completed and on-going research projects in chronological order.

Joint stereo 3D object detection and implicit surface reconstruction
Shichao Li and Kwang-Ting Cheng
Under review
Code / Pre-print

An extented study of Ego-Net, which presents the first binocular system for simultaneous outdoor 3D object detection and implicit shape estimation.

Stereo Neural Vernier Caliper
Shichao Li, Zechun Liu, Zhiqiang Shen and Kwang-Ting Cheng
Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), 2022 (15% acceptance rate)
Code / Paper / Video (1-min) / Long Talk

A novel multi-resolution approach for voxel-based stereo 3D object detection with instance-level modeling.

Exploring intermediate representation for monocular vehicle pose estimation
Shichao Li, Zengqiang Yan, Hongyang Li and Kwang-Ting Cheng
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Code / Paper / Video / Invited Talk (中文)

Ego-Net lets you recognize egocentric vehicle pose using a single RGB image.

How do Adam and training strategies help BNNs optimization
Zechun Liu, Zhiqiang Shen, Shichao Li, Koen Helwegen, Dong Huang and Kwang-Ting Cheng
International Conference on Machine Learning (ICML), 2021
Code / Paper
Cycle2GAN: Tumor-aware image-to-image translation with weak supervision
Zengqiang Yan, Shichao Li, Jeffry Wicaksana, Xin Yang and Kwang-Ting Cheng
2021

Cascaded deep monocular 3D human pose estimation with evolutionary training data
Shichao Li, Lei Ke, Kevin Pratama, Yu-Wing Tai, Chi-Keung Tang and Kwang-Ting Cheng
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (Oral presentation, 5.7% acceptance rate)
Code / Paper / Video

This is the first study on utilizing synthetic data for 2D-to-3D human pose estimation.

GSNet: joint vehicle pose and shape reconstruction with geometrical and scene-aware supervision
Lei Ke, Shichao Li, Yanan Sun, Yu-Wing Tai and Chi-Keung Tang
European Conference on Computer Vision (ECCV), 2020
Code / Paper / Video

GSNet reconstructs vehicle pose and shape jointly from a single RGB image.

Visualizing the decision-making process in deep neural decision forest
Shichao Li and Kwang-Ting Cheng
The IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops on Explainable AI, 2019
Code / Paper

How does a CNN make decision for classification/regression?

Increasing efficiency of a wireless energy transfer system by spatial translational transformation
Shichao Li, Fei Sun, Di An and Sailing He
IEEE Transactions on Power Electronics (T-PE), 2017
Paper

Numerical solution of Maxwell's equations for power transfer.

Fully coupled multiphysics simulation of crosstalk effect in bipolar resistive random access memory
Shichao Li, Yandong Luo, Wenchao Chen and Wen-Yan Yin
IEEE Transactions on Electron Devices (T-ED), 2017
Paper

A finite difference algorithm solving drift-diffusion, current continuity and heat transfer equations jointly on a uniform 3D voxel grid.

Translational illusion of acoustic sources by transformation acoustics
Fei Sun, Shichao Li and Sailing He
Journal of Acoustical Society of America, 2017
Paper

Numerical simulation of acoustic wave.

Engineering Projects

The following is a list of my past projects.

Mobile facial image analysis and augmented reality system, 2017

I developed a real-time App on Andriod platform that can perform face detection, 3D faical landmark detection, head pose estimation and simple graphics rendering. The facial landmarks were detected by a cascade of random forest with pixel-difference feature. This project does not use deep learning. It was 100% C++/Java and 0% PyTorch. :)

An object shape estimation system based on coherent light, 2016

This was an interferometry course project. A standard Michelson interferometer structure was adopted, light reflected from the unknown surface interferes with light reflected from a known surface.

An object shape estimation system based on coherent light, 2016

By moving the known surface thus changing the light path, a sequence of interference pictures were captured. This process records the surface shape in the sequence. The surface shape was recovered in the demodulation process.

An electric guitar with laser string, 2015

This was a simple micro-controller course project. Strings are made by laser diodes and photondetectors. Chord can be chosen by different buttons on this guitar. The system consists of C8051F020 (core), 74LS00 (logic), and LM386 (audio power amplifier). C8051F020 responds to user inputs and plays music stored in a SD card.

Service
comp4901j Teaching Assistant
COMP 4901J (Deep Learning for Computer Vision), Fall 2018
Lecturer: Professor Chi-Keung Tang

MSBD 6000G (Deep Learning for Computer Vision), Spring 2018
Lecturer: Professor Chi-Keung Tang

COMP 1021 (Introduction to Computer Science), Spring 2019
Lecturer: Professor David Rossitor
reviewer Conference Reviewer
CVPR, ICCV, ICML, NeurIPS, AAAI, ECCV, 3DV, WACV

Journal Reviewer
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Image Processing
International Journal of Computer Vision
Computer Vision and Image Understanding


Lebensversicherung You can get the website template here from Jon Barron.