TIANAO LI - 李天骜

I am a third-year Ph.D. candidate in Computer Science at Northwestern University, advised by Prof. Emma Alexander. I am currently funded by the NSF-Simons AI Institute for the Sky (SkAI). Previously, I received my B.Eng. in Electronic Engineering with a minor in Astronomy at Tsinghua University magna cum laude. During my undergraduate study, I was fortunate to work with Prof. Lu Fang, Prof. Emma Alexander, and Prof. Cheng Ma.

My research interest is in the field of computational imaging and photography, which lies at the intersection of optics, signal processing, computer vision, and machine learning. Specifically, I study how generative priors, scene representations, and physics-based forward modeling can advance imaging — turning ill-posed measurements into faithful reconstructions of the world. My current applications span astronomical imaging, and medical imaging, dynamic scene reconstruction, and monocular depth estimation.

I am always open to collaborations! Feel free to reach out if you want to chat about research and more.

Email  /  CV  /  Google Scholar  /  GitHub  /  X  /  LinkedIn

We introduce SpiderCam, an FPGA-based snapshot depth-from-defocus camera which produces 480x400 sparse depth maps in real-time at 32.5 FPS over a working range of 52 cm while consuming 624 mW of power in total.

We present an efficient self-supervised framework achieving state-of-the-art performance in joint reconstruction of initial pressure and speed of sound in photoacoustic computed tomography.

We introduce a physics-inspired deep learning approach that deconvolves the PSF and enables better weak gravitational lensing shear measurements for the Vera C. Rubin Observatory.

Website template from Dr. Jon Barron.