Erika Lu

Email: erikalu [at] google [dot] com

Scholar | GitHub | LinkedIn

I am currently at Google DeepMind, working on computer vision topics. Previously, I completed my PhD at the University of Oxford advised by Prof. Andrew Zisserman in the Visual Geometry Group (VGG).

Please see my Google Scholar page for an updated research list.

Research

motion-group

Self-supervised Video Object Segmentation by Motion Grouping

Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, Weidi Xie

ICCV 2021 / Paper / Project Page / Code

Short ver: CVPR Workshop on RVSU 2021 (Best Paper Award)

omnimatte

Omnimatte: Associating Objects and Their Effects in Video

Erika Lu, Forrester Cole, Tali Dekel, Andrew Zisserman, William T. Freeman, Michael Rubinstein

CVPR 2021 (Oral Presentation) / Paper / Project Page / Code

retiming

Layered Neural Rendering for Retiming People in Video

Erika Lu, Forrester Cole, Tali Dekel, Weidi Xie, Andrew Zisserman, David Salesin, William T. Freeman, Michael Rubinstein

SIGGRAPH Asia 2020 / Paper / Project Page / Code

mast

MAST: A Memory-Augmented Self-Supervised Tracker

Zihang Lai, Erika Lu, Weidi Xie

CVPR 2020 / Paper / Project Page / Code

counting

Class-Agnostic Counting

Erika Lu, Weidi Xie, Andrew Zisserman

ACCV 2018 / Paper / Project Page / Code

spotlight_vda

Learning to See Physics via Visual De-animation

Jiajun Wu, Erika Lu, Pushmeet Kohli, William T. Freeman, Joshua B. Tenenbaum

NeurIPS 2017 (Spotlight Presentation) / Paper / Project Page / MIT News