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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mei, Yiqun, He, Mingming, Ma, Li, Philip, Julien, Xian, Wenqi, George, David M, Yu, Xueming, Dedic, Gabriel, Taşel, Ahmet Levent, Yu, Ning, Patel, Vishal M., Debevec, Paul
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908295415988224
author Mei, Yiqun
He, Mingming
Ma, Li
Philip, Julien
Xian, Wenqi
George, David M
Yu, Xueming
Dedic, Gabriel
Taşel, Ahmet Levent
Yu, Ning
Patel, Vishal M.
Debevec, Paul
author_facet Mei, Yiqun
He, Mingming
Ma, Li
Philip, Julien
Xian, Wenqi
George, David M
Yu, Xueming
Dedic, Gabriel
Taşel, Ahmet Levent
Yu, Ning
Patel, Vishal M.
Debevec, Paul
contents Video portrait relighting remains challenging because the results need to be both photorealistic and temporally stable. This typically requires a strong model design that can capture complex facial reflections as well as intensive training on a high-quality paired video dataset, such as dynamic one-light-at-a-time (OLAT). In this work, we introduce Lux Post Facto, a novel portrait video relighting method that produces both photorealistic and temporally consistent lighting effects. From the model side, we design a new conditional video diffusion model built upon state-of-the-art pre-trained video diffusion model, alongside a new lighting injection mechanism to enable precise control. This way we leverage strong spatial and temporal generative capability to generate plausible solutions to the ill-posed relighting problem. Our technique uses a hybrid dataset consisting of static expression OLAT data and in-the-wild portrait performance videos to jointly learn relighting and temporal modeling. This avoids the need to acquire paired video data in different lighting conditions. Our extensive experiments show that our model produces state-of-the-art results both in terms of photorealism and temporal consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14485
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset
Mei, Yiqun
He, Mingming
Ma, Li
Philip, Julien
Xian, Wenqi
George, David M
Yu, Xueming
Dedic, Gabriel
Taşel, Ahmet Levent
Yu, Ning
Patel, Vishal M.
Debevec, Paul
Graphics
Computer Vision and Pattern Recognition
Video portrait relighting remains challenging because the results need to be both photorealistic and temporally stable. This typically requires a strong model design that can capture complex facial reflections as well as intensive training on a high-quality paired video dataset, such as dynamic one-light-at-a-time (OLAT). In this work, we introduce Lux Post Facto, a novel portrait video relighting method that produces both photorealistic and temporally consistent lighting effects. From the model side, we design a new conditional video diffusion model built upon state-of-the-art pre-trained video diffusion model, alongside a new lighting injection mechanism to enable precise control. This way we leverage strong spatial and temporal generative capability to generate plausible solutions to the ill-posed relighting problem. Our technique uses a hybrid dataset consisting of static expression OLAT data and in-the-wild portrait performance videos to jointly learn relighting and temporal modeling. This avoids the need to acquire paired video data in different lighting conditions. Our extensive experiments show that our model produces state-of-the-art results both in terms of photorealism and temporal consistency.
title Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.14485