Ang Li

I am a MSCS student at Stanford University. Previously I was an undergraduate student major in computer science at UC San Diego. I was fortunate to be advised by Prof. Hao Su.

I am broadly interested in computer vision, robotics and computer graphics.

CV  /  Email  /  GitHub

We lower the sim-to-real gap of simulated depth and real active stereovision depth sensors, by designing a fully physics-grounded pipeline. Perception and RL methods trained in simulation can transfer well to the real world without any fine-tuning. It can also estimate the algorithm performance in the real world, largely reducing human effort of algorithm evaluation.

SimSense is a GPU-accelerated depth sensor simulator for python, implemented with CUDA. Based on semi-global matching, SimSense encapsulated various algorithms to compute depth from a pair of stereo images. It can achieve over 250 FPS whereas usual CPU implementations can hardly achieve 1 fps. This library has been integrated into the open-source simulation environment SAPIEN.

This is the final project for my course CSE 291: Machine Learning for 3D Geometry at UCSD, in which I reproduced Neural Radiance Fields on the bottles dataset.

A Multi-Vew Stereo reconstruction pipeline implemented with OpenCV and Open3D. I designed this pipeline to be used as the final assignment for the class CSE 152A: Introduction to Computer Vision of Fall 2021 at UCSD.

Instructional Assistant for CSE 152A: Introduction to Computer Vision of 2022 Fall at UCSD. Instructor: Manmohan Chandraker

Modified from Jon Barron's personal website.