Saved in:
Bibliographic Details
Main Authors: Wang, Junying, Liu, Jingyuan, Sun, Xin, Singh, Krishna Kumar, Shu, Zhixin, Zhang, He, Yang, Jimei, Zhao, Nanxuan, Wang, Tuanfeng Y., Chen, Simon S., Neumann, Ulrich, Yoon, Jae Shin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.03011
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • This paper introduces Comprehensive Relighting, the first all-in-one approach that can both control and harmonize the lighting from an image or video of humans with arbitrary body parts from any scene. Building such a generalizable model is extremely challenging due to the lack of dataset, restricting existing image-based relighting models to a specific scenario (e.g., face or static human). To address this challenge, we repurpose a pre-trained diffusion model as a general image prior and jointly model the human relighting and background harmonization in the coarse-to-fine framework. To further enhance the temporal coherence of the relighting, we introduce an unsupervised temporal lighting model that learns the lighting cycle consistency from many real-world videos without any ground truth. In inference time, our temporal lighting module is combined with the diffusion models through the spatio-temporal feature blending algorithms without extra training; and we apply a new guided refinement as a post-processing to preserve the high-frequency details from the input image. In the experiments, Comprehensive Relighting shows a strong generalizability and lighting temporal coherence, outperforming existing image-based human relighting and harmonization methods.