Runfeng Li

Hi, I am a first-year Ph.D. student in Electrical and Computer Engineering at Rice University.

Before this, I did my Master's in Computer Science at Brown University, where I worked with Prof. James Tompkin, and collaborated with Prof. Matthew O'Toole and Dr. Christian Richardt. I earned my Bachelor's in Mathematics and Computer Science from University of Illinois Urbana-Champaign.

Email: runfeng_li [at] rice [dot] edu

GitHub  /  Google Scholar  /  CV  /  LinkedIn

Research

I have spent much of the last few years on things like this. It uses a LiDAR-like camera to reconstruct 3D scenes, though, hilariously, I have only physically touched the camera once in my life.

Currently, I am broadly interested in computational photography and imaging, computer vision, and machine learning.

We show that radiance field reconstruction from single-frequency continuous-wave raw time-of-flight images is fundamentally ill-posed. However, we find optimization biases in the 3D-Gaussian-parameterized radiance fields that reasonably regularize the geometry. We then exploit this finding to reconstruct dynamic scenes like fast-swinging baseball bats with quality comparable to or better than prior neural-field-based methods while retaining the efficiency of Gaussians.

We benchmark dynamic Gaussian splatting methods for monocular view synthesis, combining existing datasets and a new synthetic dataset to provide standardized comparisons and identify key factors affecting efficiency and quality.

Other Past Interests

We estimate Young's modulus by backpropagating video-reconstruction gradients through our Taichi implementation of PhysGaussian.

Reference: Jon Barron's Template.