# AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing

arXiv: https://arxiv.org/abs/2603.26546 · HTML: https://mlsanity.com/paper/2603.26546/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 82 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [ADriver-I: A General World Model for Autonomous Driving](https://mlsanity.com/paper/2311.13549/) (2023)
- [Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset](https://mlsanity.com/paper/2510.15742/) (2025)
- [OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving](https://mlsanity.com/paper/2405.20337/) (2024)
- [Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation](https://mlsanity.com/paper/2406.01349/) (2024)
- [R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation](https://mlsanity.com/paper/2506.07826/) (2025)
- [WeatherEdit: Controllable Weather Editing with 4D Gaussian Field](https://mlsanity.com/paper/2505.20471/) (2025)
- [Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory](https://mlsanity.com/paper/2407.20785/) (2024)
- [CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis](https://mlsanity.com/paper/2509.06579/) (2025)
- [Weather-Magician: Reconstruction and Rendering Framework for 4D Weather Synthesis In Real Time](https://mlsanity.com/paper/2505.19919/) (2025)
- [IntrinsicWeather: Controllable Weather Editing in Intrinsic Space](https://mlsanity.com/paper/2508.06982/) (2025)

## Built on by (most cited first, 4 of 4)

- [Holo-World: Unified Camera, Object and Weather Control for Video World Model](https://mlsanity.com/paper/2606.20083/) (2026)
- [muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards](https://mlsanity.com/paper/2608.04412/) (2026)
- [RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models](https://mlsanity.com/paper/2608.02953/) (2026)
- [DistScene: Object-to-Scene Distillation for 3D Scene Generation](https://mlsanity.com/paper/2610.06960/) (2026)

## Abstract (arXiv)

Generative video models have significantly advanced the photorealistic synthesis of adverse weather for autonomous driving; however, they consistently demand massive datasets to learn rare weather scenarios. While 3D-aware editing methods alleviate these data constraints by augmenting existing video footage, they are fundamentally bottlenecked by costly per-scene optimization and suffer from inherent geometric and illumination entanglement. In this work, we introduce AutoWeather4D, a feed-forward 3D-aware weather editing framework designed to explicitly decouple geometry and illumination. At the core of our approach is a G-buffer Dual-pass Editing mechanism. The Geometry Pass leverages explicit structural foundations to enable surface-anchored physical interactions, while the Light Pass analytically resolves light transport, accumulating the contributions of local illuminants into the global illumination to enable dynamic 3D local relighting. Extensive experiments demonstrate that AutoWeather4D achieves comparable photorealism and structural consistency to generative baselines while enabling fine-grained parametric physical control, serving as a practical data engine for autonomous driving.