# DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

arXiv: https://arxiv.org/abs/2503.15208 · HTML: https://mlsanity.com/paper/2503.15208/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 63 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 30 of 55)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis](https://mlsanity.com/paper/2409.02048/) (2024)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control](https://mlsanity.com/paper/2503.03751/) (2025)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)
- [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving](https://mlsanity.com/paper/2309.09777/) (2023)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving](https://mlsanity.com/paper/2311.16038/) (2023)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [OmniRe: Omni Urban Scene Reconstruction](https://mlsanity.com/paper/2408.16760/) (2024)
- [Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering](https://mlsanity.com/paper/2311.18561/) (2023)
- [DriveGAN: Towards a Controllable High-Quality Neural Simulation](https://mlsanity.com/paper/2104.15060/) (2021)
- [DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation](https://mlsanity.com/paper/2410.13571/) (2024)
- [TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers](https://mlsanity.com/paper/2111.14600/) (2021)

## Built on by (most cited first, 30 of 40)

- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [DriveLaW:Unifying Planning and Video Generation in a Latent Driving World](https://mlsanity.com/paper/2512.23421/) (2025)
- [OmniNWM: Omniscient Driving Navigation World Models](https://mlsanity.com/paper/2510.18313/) (2025)
- [Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving](https://mlsanity.com/paper/2603.24581/) (2026)
- [GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation](https://mlsanity.com/paper/2512.23180/) (2025)
- [DVGT: Driving Visual Geometry Transformer](https://mlsanity.com/paper/2512.16919/) (2025)
- [X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability](https://mlsanity.com/paper/2506.13558/) (2025)
- [WorldGen: From Text to Traversable and Interactive 3D Worlds](https://mlsanity.com/paper/2511.16825/) (2025)
- [Challenger: Affordable Adversarial Driving Video Generation](https://mlsanity.com/paper/2505.15880/) (2025)
- [WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving](https://mlsanity.com/paper/2509.23402/) (2025)
- [Light-X: Generative 4D Video Rendering with Camera and Illumination Control](https://mlsanity.com/paper/2512.05115/) (2025)
- [CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving](https://mlsanity.com/paper/2605.10426/) (2026)
- [CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting](https://mlsanity.com/paper/2507.18473/) (2025)
- [GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting](https://mlsanity.com/paper/2507.19451/) (2025)
- [LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model](https://mlsanity.com/paper/2506.01546/) (2025)
- [4D Driving Scene Generation With Stereo Forcing](https://mlsanity.com/paper/2509.20251/) (2025)
- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [Is Your Driving World Model an All-Around Player?](https://mlsanity.com/paper/2605.10858/) (2026)
- [RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space](https://mlsanity.com/paper/2602.20685/) (2026)
- [From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation](https://mlsanity.com/paper/2605.08712/) (2026)
- [GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation](https://mlsanity.com/paper/2511.23191/) (2025)
- [FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous Driving](https://mlsanity.com/paper/2603.14938/) (2026)
- [HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation](https://mlsanity.com/paper/2604.28196/) (2026)
- [UniUncer: Unified Dynamic Static Uncertainty for End to End Driving](https://mlsanity.com/paper/2603.07686/) (2026)
- [OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation](https://mlsanity.com/paper/2606.17536/) (2026)
- [OpenLongTail: Generative Scaling of Long-Tail Driving Data](https://mlsanity.com/paper/2607.09655/) (2026)
- [Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction](https://mlsanity.com/paper/2605.22420/) (2026)
- [Future Dynamic 3D Reconstruction: Toward 3D World Modeling with Disentangled Ego-Motion](https://mlsanity.com/paper/2606.18250/) (2026)
- [FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model](https://mlsanity.com/paper/2606.20110/) (2026)
- [Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation](https://mlsanity.com/paper/2607.06516/) (2026)

## Abstract (arXiv)

Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. A key challenge lies in finding an efficient and generalizable geometric representation that seamlessly connects temporal and spatial synthesis. To address this, we propose DiST-4D, the first disentangled spatiotemporal diffusion framework for 4D driving scene generation, which leverages metric depth as the core geometric representation. DiST-4D decomposes the problem into two diffusion processes: DiST-T, which predicts future metric depth and multi-view RGB sequences directly from past observations, and DiST-S, which enables spatial NVS by training only on existing viewpoints while enforcing cycle consistency. This cycle consistency mechanism introduces a forward-backward rendering constraint, reducing the generalization gap between observed and unseen viewpoints. Metric depth is essential for both accurate reliable forecasting and accurate spatial NVS, as it provides a view-consistent geometric representation that generalizes well to unseen perspectives. Experiments demonstrate that DiST-4D achieves state-of-the-art performance in both temporal prediction and NVS tasks, while also delivering competitive performance in planning-related evaluations.