Xiaojuan Wang

I'm a Ph.D student in GRAIL, University of Washington, advised by Steve Seitz, Brian Curless and Ira Kemelmacher.

Previously, I received my Master's degree from ETH Zurich, working in the CVG lab. I have also interned at Meta, Adobe Research with Richard Zhang Taesung Park , and Google Research with Aleksander Holynski during summers.

I am broadly interested in generative AI, especially AI for video content creation.

Email  /  CV  /  Scholar  /  Twitter  /  Github

profile photo

Selected Publications

Generative Powers of Ten
Xiaojuan Wang, Janne Kontkanen, Brian Curless, Steve Seitz, Ira Kemelmacher, Ben Mildenhall, Pratul P. Srinivasan, Dor Verbin, Aleksander Holynski
CVPR, 2024 (Highlight)
project page / arXiv

Given a series of prompts describing a scene at drastically varying scales, our method creates a seamless zooming video.

Jump Cut Smoothing for Talking Heads
Xiaojuan Wang, Taesung Park, Yang Zhou, Eli Shechtman, Richard Zhang
arXiv, 2023
project page / arXiv

Given a talking head video, we remove the the filler words, repetitive words and so on, and create a seamless transition for the jump cut.

Learning 3D Semantic Reconstruction on Octrees
Xiaojuan Wang, Martin Oswald, Ian Cherabier, Marc Pollefeys
GCPR, 2019

We present a novel framework for multi-view semantic 3D reconstruction that takes the octree of TSDFs fused from different camera views as input, and generates an octree as semantic reconstruction output.

Other Works

Supervised quantization for similarity search (CVPR 2016)
Multi-scale learning for low-resolution person re-identification (ICCV 2015)
Cross-scenario transfer person reidentification (TCSVT 2015)


My first name in Chinese is 小鹃,which means "a little cuckoo bird". You can also call me "jeanne".
I am a big movie fan of Quentin Tarantino and Christopher Nolan.
I travel a lot, and enjoy spending time in the musuem.

This website borrows the template from Jon Barron