Wenqi (Wendy) Xian

I'm a Research Scientist at Luma AI working on generative video for creative production. Before this, I was a researcher on Paul Debevec's Eyeline Lab at Netflix, where I worked on photorealistic reconstruction and relighting for virtual production.

I received my Ph.D. from Cornell Tech in 2023, advised by Noah Snavely. Before that, I received my B.S. from Georgia Institute of Technology in 2018.

My research focuses on AI for filmmaking — from lights, to camera, to action. I'm interested in controllable, multi-modal video diffusion models that filmmakers can actually direct, not just prompt.

Outside of research, I enjoy being outdoors — skiing, diving, and climbing.

News

Dec 2025	Joined Luma AI as Research Scientist! We are hiring for full-time and internship roles, please reach out if you are interested.
Dec 2025	2 papers accepted to SIGGRAPH Asia 2025: DEGS and Virtually Being.
Nov 2025	Invited to give a guest lecture for Deep Learning for Computer Vision at UCLA.
Oct 2025	2 papers accepted to ICCV 2025 as Highlights: FlashDepth and Self-Calibrating Gaussian Splatting.

Publications

Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture

Julien Philip*, Li Ma*, Pascal Clausen*, Wenqi Xian*, Ahmet Levent Taşel, Mingming He, Xueming Yu, David M. George, Ning Yu, Oliver Pilarski, Paul Debevec

SIGGRAPH Asia 2025

Project Paper

Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures

Yuancheng Xu, Wenqi Xian, Li Ma, Julien Philip, Ahmet Taşel, Yiwei Zhao, Ryan Burgert, Mingming He, Oliver Hermann, Oliver Pilarski, Rahul Garg, Paul Debevec, Ning Yu

SIGGRAPH Asia 2025

Project Paper

FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution

Gene Chou, Wenqi Xian, Guandao Yang, Mohamed Abdelfattah, Bharath Hariharan, Noah Snavely, Ning Yu, Paul Debevec

ICCV 2025 Highlight

Project Paper Code

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

Ryan Burgert, Yuancheng Xu, Wenqi Xian, Oliver Pilarski, Pascal Clausen, Mingming He, Li Ma, Yitong Deng, Lingxiao Li, Mohsen Mousavi, Michael Ryoo, Paul Debevec, Ning Yu

CVPR 2025 Oral

Project Paper Code

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction

Youming Deng, Wenqi Xian, Guandao Yang, Leonidas Guibas, Gordon Wetzstein, Steve Marschner, Paul Debevec

ICCV 2025 Highlight

Project Paper Code

Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset

Yiqun Mei, Mingming He, Li Ma, Julien Philip, Wenqi Xian, David M George, Xueming Yu, Gabriel Dedic, Ahmet Levent Taşel, Ning Yu, Vishal M. Patel, Paul Debevec

CVPR 2025

Project Paper

DifFRelight: Diffusion-Based Facial Performance Relighting

Mingming He*, Pascal Clausen*, Ahmet Levent Taşel*, Li Ma*, Oliver Pilarski*, Wenqi Xian, Laszlo Rikker, Xueming Yu, Ryan Burgert, Ning Yu, Paul Debevec

SIGGRAPH Asia 2024

Project Paper