Light4D：无需训练的极端视角4D视频重光照技术

Light4D: Training-Free Extreme Viewpoint 4D Video Relighting

February 12, 2026

作者: Zhenghuang Wu, Kang Chen, Zeyu Zhang, Hao Tang

cs.AI

摘要

基于扩散的生成模型最新进展为图像与视频重照明确立了新范式。然而，将这些能力拓展至四维重照明仍面临挑战，主要源于配对4D重照明训练数据的稀缺性，以及在极端视角变化下保持时间一致性的困难。本研究提出Light4D——一种无需训练的新型框架，可在目标光照下合成具有时间一致性的4D视频，即使面临极端视角变化也能保持稳定。首先，我们引入解耦流引导策略，这种时序感知方法能有效将光照控制注入潜在空间，同时保持几何完整性。其次，为增强时间一致性，我们在IC-Light架构中开发了时序一致注意力机制，并进一步引入确定性正则化以消除画面闪烁。大量实验表明，本方法在时间一致性与光照保真度方面达到业界先进水平，可稳健处理-90°至90°的摄像机旋转。代码与项目网站详见文末链接。

English

Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities to 4D relighting remains challenging, due primarily to the scarcity of paired 4D relighting training data and the difficulty of maintaining temporal consistency across extreme viewpoints. In this work, we propose Light4D, a novel training-free framework designed to synthesize consistent 4D videos under target illumination, even under extreme viewpoint changes. First, we introduce Disentangled Flow Guidance, a time-aware strategy that effectively injects lighting control into the latent space while preserving geometric integrity. Second, to reinforce temporal consistency, we develop Temporal Consistent Attention within the IC-Light architecture and further incorporate deterministic regularization to eliminate appearance flickering. Extensive experiments demonstrate that our method achieves competitive performance in temporal consistency and lighting fidelity, robustly handling camera rotations from -90 to 90. Code: https://github.com/AIGeeksGroup/Light4D. Website: https://aigeeksgroup.github.io/Light4D.