Salvato in:
Dettagli Bibliografici
Autori principali: Gao, Wenshuo, Fan, Junyi, Zeng, Jiangyue, Yang, Shuai
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.18346
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912726150807552
author Gao, Wenshuo
Fan, Junyi
Zeng, Jiangyue
Yang, Shuai
author_facet Gao, Wenshuo
Fan, Junyi
Zeng, Jiangyue
Yang, Shuai
contents Video relighting with background replacement is a challenging task critical for applications in film production and creative media. Existing methods struggle to balance temporal consistency, spatial fidelity, and illumination naturalness. To address these issues, we introduce FlowPortal, a novel training-free flow-based video relighting framework. Our core innovation is a Residual-Corrected Flow mechanism that transforms a standard flow-based model into an editing model, guaranteeing perfect reconstruction when input conditions are identical and enabling faithful relighting when they differ, resulting in high structural consistency. This is further enhanced by a Decoupled Condition Design for precise lighting control and a High-Frequency Transfer mechanism for detail preservation. Additionally, a masking strategy isolates foreground relighting from background pure generation process. Experiments demonstrate that FlowPortal achieves superior performance in temporal coherence, structural preservation, and lighting realism, while maintaining high efficiency. Project Page: https://gaowenshuo.github.io/FlowPortalProject/.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
Gao, Wenshuo
Fan, Junyi
Zeng, Jiangyue
Yang, Shuai
Computer Vision and Pattern Recognition
Video relighting with background replacement is a challenging task critical for applications in film production and creative media. Existing methods struggle to balance temporal consistency, spatial fidelity, and illumination naturalness. To address these issues, we introduce FlowPortal, a novel training-free flow-based video relighting framework. Our core innovation is a Residual-Corrected Flow mechanism that transforms a standard flow-based model into an editing model, guaranteeing perfect reconstruction when input conditions are identical and enabling faithful relighting when they differ, resulting in high structural consistency. This is further enhanced by a Decoupled Condition Design for precise lighting control and a High-Frequency Transfer mechanism for detail preservation. Additionally, a masking strategy isolates foreground relighting from background pure generation process. Experiments demonstrate that FlowPortal achieves superior performance in temporal coherence, structural preservation, and lighting realism, while maintaining high efficiency. Project Page: https://gaowenshuo.github.io/FlowPortalProject/.
title FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.18346