Tianfu Wang 王天夫

I am a first year PhD student in the University of Maryland, College Park supervised by Prof. Christopher Metzler.

Previously I was a master student in ETH Zürich where I worked with Anton Obukhov, Menelaos Kanakis, Prof. Konrad Schindler, and Prof. Luc Van Gool on NeRF and diffusion models.

Prior to that, I obtained my undergraduate degree from Northwestern University. I worked with Prof. Oliver Cossairt and Prof. Florian Willomitzer. I was also fortunate to work with Prof. Jack Tumblin, who inspired my interest in visual commputing.

I am always enthusiastic about building and utilizing intelligent systems that not only help us understand and better represent our 3D world, but also allow us to craft our own virtual realms. More specifically, my research interest lies at the crossroads of graphics, vision, and computational photography, including areas such as neural and inverse rendering, generative AI in computer vision, and innovations in imaging and optics.

Email  /  CV  /  Scholar  /  Github  /  LinkedIn

A robust 2D reflection removal method leveraging physical flash/no-flash cues with latent-space diffusion separation.

Fine-tuneing a pre-trained video diffusion model on event camera data turns it into a state-of-the-art event-based video interpolater and extrapolator with high temporal resolution.

We present a accurate and fast gaze tracking method using single-shot phase-measuring-deflectometry (PMD), taking advantage of dense 3D surface measurements of the eye surface.

We specialize a pre-trained latent diffusion model into an efficient data generation pipeline with style control and multi-resolution semantic adherence, improving downstream domain generalization performance.

Using a differentiable renderer to simulate reflection light transport allows us to take advantage of dense sturctured screen illumination to accurately optimize eye gaze direction.

Our method lifts the power of generative 2D image models, such as Stable Diffusion, into 3D. Using them as a way to synthesize unseen content for novel views, and NeRF to reconcile all generated views, our method provides vivid painting of the input 3D assets in a variety of shape categories.

We present a first study on the trade-offs between projection and reflection based 3D imaging systems under diffusive and specular reflection mixtures. Experiments are conducted in our projection/reflection simulator framework using the Mitsuba2 renderer.

Cool Stuff

Metaballs meet Smooth Particle Hydrodynamics (SPH)

Misc

Aside from research, I delight in the symphony of flavors that dance on the tongue (good food) and the harmonious melodies that serenade the ears (music). A few of my musical heroes include 竇唯 (Dou Wei), Radiohead, Brian Eno, and Fleet Foxes.

This is a Jon Barron website. Thanks Jon!