Relightful Video Portrait Harmonization
Jun Myeong Choi, Jae Shin Yoon, Luchao Qi, Roni Sengupta, Joon-Young Lee
2026年份
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper30
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video GenerationJay Zhangjie Wu, Yixiao Ge, Xintao Wang, Stan Weixian Lei 等ICCV 2023 · 被引用 1,113 次
- Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video GeneratorsLevon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel 等ICCV 2023 · 被引用 800 次
- Deep Single-Image Portrait RelightingHao Zhou, Sunil Hadap, Kalyan Sunkavalli, David JacobsICCV 2019 · 被引用 247 次
- Total relighting: learning to relight portraits for background replacementRohit Pandey, Sergio Orts-Escolano, Chloe LeGendre, Christian Häne 等SIGGRAPH 2021 · 被引用 138 次
相关 Paper
- Relightful Harmonization: Lighting-Aware Portrait Background ReplacementMengwei Ren, Wei Xiong, Jae Shin Yoon, Zhixin Shu 等CVPR 2024 · 被引用 17 次
- Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and HarmonizationJunying Wang, Jingyuan Liu, Xin Sun, Krishna Kumar Singh 等CVPR 2025
- CFDiffusion: Controllable Foreground Relighting in Image Compositing via Diffusion ModelZiqi Yu, Jing Zhou, Zhongyun Bao, Gang Fu 等ACM MM 2024 · 被引用 6 次
- Video Harmonization with Triplet Spatio-Temporal Variation PatternsZonghui Guo, Xinyu Han, Jie Zhang, Shiguang Shan 等CVPR 2024
- Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting ReproductionYufan Zhang, Yu Ji, Ayo Ajiboye, Rundi Wu 等SIGGRAPH 2026
