# Light4D: Training-Free Extreme Viewpoint 4D Video Relighting

arXiv: https://arxiv.org/abs/2602.11769 · HTML: https://mlsanity.com/paper/2602.11769/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling](https://mlsanity.com/paper/2311.17984/) (2023)
- [SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting](https://mlsanity.com/paper/2402.18848/) (2024)
- [LightIt: Illumination Modeling and Control for Diffusion Models](https://mlsanity.com/paper/2403.10615/) (2024)
- [Neural Video Portrait Relighting in Real-time via Consistency Modeling](https://mlsanity.com/paper/2104.00484/) (2021)
- [Relighting4D: Neural Relightable Human from Videos](https://mlsanity.com/paper/2207.07104/) (2022)
- [Light-A-Video: Training-free Video Relighting via Progressive Light Fusion](https://mlsanity.com/paper/2502.08590/) (2025)
- [DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes](https://mlsanity.com/paper/2410.18084/) (2024)
- [LightLab: Controlling Light Sources in Images with Diffusion Models](https://mlsanity.com/paper/2505.09608/) (2025)
- [4DNeX: Feed-Forward 4D Generative Modeling Made Easy](https://mlsanity.com/paper/2508.13154/) (2025)
- [EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh](https://mlsanity.com/paper/2506.05554/) (2025)
- [RelightVid: Temporal-Consistent Diffusion Model for Video Relighting](https://mlsanity.com/paper/2501.16330/) (2025)
- [SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces](https://mlsanity.com/paper/2501.09756/) (2025)
- [GenLit: Reformulating Single-Image Relighting as Video Generation](https://mlsanity.com/paper/2412.11224/) (2024)
- [Disco4D: Disentangled 4D Human Generation and Animation from a Single Image](https://mlsanity.com/paper/2409.17280/) (2024)
- [DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows](https://mlsanity.com/paper/2304.09479/) (2023)
- [Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization](https://mlsanity.com/paper/2504.03011/) (2025)
- [Light-X: Generative 4D Video Rendering with Camera and Illumination Control](https://mlsanity.com/paper/2512.05115/) (2025)
- [Relightable Neural Actor with Intrinsic Decomposition and Pose Control](https://mlsanity.com/paper/2312.11587/) (2023)
- [HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation](https://mlsanity.com/paper/2504.21650/) (2025)
- [One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control](https://mlsanity.com/paper/2511.18922/) (2025)
- [BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading](https://mlsanity.com/paper/2506.06271/) (2025)
- [BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video](https://mlsanity.com/paper/2502.08297/) (2025)
- [DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling](https://mlsanity.com/paper/2512.03000/) (2025)
- [OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis](https://mlsanity.com/paper/2512.10940/) (2025)
- [DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting](https://mlsanity.com/paper/2504.10486/) (2025)
- [Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular Video](https://mlsanity.com/paper/2512.09335/) (2025)

## Built on by (most cited first, 2 of 2)

- [UniMesh: Unifying 3D Mesh Understanding and Generation](https://mlsanity.com/paper/2604.17472/) (2026)
- [FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation](https://mlsanity.com/paper/2603.27915/) (2026)

## Abstract (arXiv)

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.