Xuanchen Lu

Hi! I am a PhD student at the University of Michigan, advised by Prof. Andrew Owens. My research lies at the intersection of computer vision and human vision.

Before starting my PhD, I was a researcher in Prof. Wang's lab at UC San Diego and the Cognitive Tools Lab at Stanford University.

I received my Master's degree in Computer Science from UC San Diego, co-advised by Prof. Judith Fan and Prof. Xiaolong Wang. I also obtained my Bachelor's degree from UC San Diego where I studied Computer Science, Mathematics, and Cognitive Science (minor).

Email  /  Google Scholar /  GitHub  /  Twitter

Research

In early infancy, babies learn to track moving objects, gaze at unlikely events, and develop an understanding of object permanence and solidity. Through this process, they acquire knowledge about the categories, functions, motions, and intuitive physics of elements in the environment.

Can artificial vision systems achieve a comparable level of visual understanding by observing the world through videos? This question naturally involves learning world models from continuous visual observations with minimal supervision.

Therefore, my research interests reside at the intersection of self-supervised learning from videos, understanding structures of the physical world, and human visual perception (e.g. visual abstraction).

(* indicates equal contribution)

SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction

Learning Dense Correspondences between Photos and Sketches

Visual explanations prioritize functional properties at the expense of visual fidelity

Evaluating machine comprehension of sketch meaning at different levels of abstraction

Evaluating machine comprehension of sketch meaning at different levels of abstraction

Design and source code from Jon Barron's website