Relightful Video Portrait Harmonization
Jun Myeong Choi, Jae Shin Yoon, Luchao Qi, Roni Sengupta, Joon-Young Lee
Abstract
Figure 1. We present HarmoVid, a relightable video harmonization framework that aligns lighting between foreground and background. Given a foreground video with masks and a target background video, HarmoVid leverages a video diffusion model to directly synthesize a harmonized output. It produces realistic, temporally consistent results that accurately match foreground color, intensity, and shadows to the background while preserving both foreground and background content.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 6a7bed38-49e8-4c80-9267-199caf91834eBuilds on30
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video GenerationJay Zhangjie Wu, Yixiao Ge, Xintao Wang, Stan Weixian Lei et al.ICCV 2023 · 1,113 citations
- Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video GeneratorsLevon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel et al.ICCV 2023 · 800 citations
- Deep Single-Image Portrait RelightingHao Zhou, Sunil Hadap, Kalyan Sunkavalli, David JacobsICCV 2019 · 247 citations
- Total relighting: learning to relight portraits for background replacementRohit Pandey, Sergio Orts-Escolano, Chloe LeGendre, Christian Häne et al.SIGGRAPH 2021 · 138 citations
Related papers
- Relightful Harmonization: Lighting-Aware Portrait Background ReplacementMengwei Ren, Wei Xiong, Jae Shin Yoon, Zhixin Shu et al.CVPR 2024 · 17 citations
- Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and HarmonizationJunying Wang, Jingyuan Liu, Xin Sun, Krishna Kumar Singh et al.CVPR 2025
- CFDiffusion: Controllable Foreground Relighting in Image Compositing via Diffusion ModelZiqi Yu, Jing Zhou, Zhongyun Bao, Gang Fu et al.ACM MM 2024 · 6 citations
- Video Harmonization with Triplet Spatio-Temporal Variation PatternsZonghui Guo, Xinyu Han, Jie Zhang, Shiguang Shan et al.CVPR 2024
- Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting ReproductionYufan Zhang, Yu Ji, Ayo Ajiboye, Rundi Wu et al.SIGGRAPH 2026
