Vickie Ye


cv | google scholar | github
email: vye [at] berkeley (dot) edu

I am a fifth year PhD student in Electrical Engineering and Computer Science at UC Berkeley in the Berkeley AI Research Lab. I am fortunate to be advised by Angjoo Kanazawa, and supported by the NSF Graduate Research Fellowship. I spent the summer of 2021 at Google Research with Noah Snavely working on methods for understanding the moving elements in videos.

My current research interests lie at the intersection between computer vision, computer graphics, and machine learning. Specifically, I'm interested understanding the world in 3D, moving beyond our current grasp in 2D or 2.5D, to facilitate reconstruction and understanding from diverse viewpoints. Previously, I worked on topics in control and learning theory.

I received a B.S. in Computer Science and Physics (2017), and an M.Eng in Electrical Engineering and Computer Science (2018) at MIT, where I was fortunate to work with Bill Freeman and Katie Bouman in computational photography.

Publications

Decoupling Human and Camera Motion from Videos in the Wild

V Ye, G Pavlakos, J Malik, A Kanazawa.
Conference on Computer Vision and Pattern Recognition (CVPR) 2023.
(website) (paper)

Deformable Sprites for Unsupervised Video Decomposition

V Ye, Z Li, R Tucker, A Kanazawa, N Snavely.
Conference on Computer Vision and Pattern Recognition (CVPR) 2022. Oral.
(website) (paper) (video)

PixelNeRF: Neural Radiance Fields from One or Few Images

A Yu, V Ye, M Tancik, A Kanazawa.
Conference on Computer Vision and Pattern Recognition (CVPR) 2021.
(website) (paper) (video)

Robust Guarantees for Perception-based Control.

S Dean, N Matni, B Recht, V Ye. (α - β order).
Conference on Learning for Dynamics and Control (L4DC) 2020.
(paper) (code)

Inferring Light Fields from Shadows.

M Baradad, V Ye, A Yedidia, GW Wornell, WT Freeman, A Torralba.
Conference on Computer Vision and Pattern Recognition (CVPR) 2018.
(paper)

Turning Corners into Cameras: Principles and Methods.

KL Bouman, V Ye, A Yedidia, A Torralba, GW Wornell, WT Freeman.
International Conference on Computer Vision (ICCV) 2017, Spotlight Presentation.
(paper) (code)