Jingwang Ling

Hi! I’m a Ph.D. student in Computer Science at University of Illinois Urbana-Champaign (UIUC), specializing in computer graphics and vision. I am advised by Prof. Shuang Zhao. I received my bachelor’s degree from School of Software, Tsinghua University, where I was fortunate to be advised by Prof. Feng Xu.

Email  /  Github  /  Google Scholar  /  LinkedIn

My research focuses on digitalizing the 3D world from images through physics-based inverse rendering. To achieve this, I integrate three key components: accurate physics-based rendering models to ensure physical correctness, generative priors to introduce data-driven regularization, and real-world measurements to anchor reconstruction in observation.

We treat a diffusion model's material predictions as a similarity kernel for regularization, jointly reconstructing geometry, materials, and illumination that relight faithfully.

Using a NeRF to capture spatially varying illumination in inverse rendering improves 3D reconstruction under non-distant lighting.

The essence of NeRF is supervising camera rays. This ray supervision scheme can generalize to shadow rays, enabling neural scene reconstruction from single-view shadows.

A generative model of 3D facial details that can perform expression, age and wrinkle line editing.

A facial detail morphable model that augments 3DMMs in detail reconstruction and animation.

A real-time tracking system that updates user-specific facial blendshapes with fine-scale details and preserves emotion semantics.

The website's template is borrowed from Jon Barron. Thank you!