Light4D：免训练的四维视频极端视角重光照技术

摘要

基于扩散的生成模型最新进展为图像和视频重照明建立了新范式。然而，将这些能力扩展到四维重照明仍面临挑战，主要源于配对四维重照明训练数据的稀缺性，以及在极端视角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，能在目标光照下合成具有时间一致性的四维视频，即使面临极端视角变化。首先，我们引入解耦流引导策略，这种时间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架构内开发了时序一致注意力机制，并进一步结合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均达到业界竞争力，可稳健处理-90°至90°的摄像机旋转。代码：https://github.com/AIGeeksGroup/Light4D 项目网站：https://aigeeksgroup.github.io/Light4D

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.

Light4D：免训练的四维视频极端视角重光照技术

Light4D: Training-Free Extreme Viewpoint 4D Video Relighting

摘要

Support