Abstract
Light4D enables consistent 4D video synthesis under target illumination through disentangled flow guidance and temporal consistent attention mechanisms.
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.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Hi-Light: A Path to high-fidelity, high-resolution video relighting with a Novel Evaluation Paradigm (2026)
- SyncLight: Controllable and Consistent Multi-View Relighting (2026)
- FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Geometry-Complete 4D Reconstruction (2026)
- Ctrl&Shift: High-Quality Geometry-Aware Object Manipulation in Visual Generation (2026)
- LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models (2026)
- Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes (2025)
- CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper