# DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images

arXiv: https://arxiv.org/abs/2512.03004 · HTML: https://mlsanity.com/paper/2512.03004/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2025.

## Built on by (most cited first, 24 of 24)

- [NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results](https://mlsanity.com/paper/2604.04135/) (2026)
- [Vision Pretraining for Dense Spatial Perception](https://mlsanity.com/paper/2607.05247/) (2026)
- [ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction](https://mlsanity.com/paper/2603.07552/) (2026)
- [VG3S: Visual Geometry Grounded Gaussian Splatting for Semantic Occupancy Prediction](https://mlsanity.com/paper/2603.06210/) (2026)
- [Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving](https://mlsanity.com/paper/2605.18137/) (2026)
- [Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation](https://mlsanity.com/paper/2607.14203/) (2026)
- [Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes](https://mlsanity.com/paper/2605.04435/) (2026)
- [ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories](https://mlsanity.com/paper/2512.03621/) (2025)
- [Risk-Controllable Multi-View Diffusion for Driving Scenario Generation](https://mlsanity.com/paper/2603.11534/) (2026)
- [PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations](https://mlsanity.com/paper/2605.11594/) (2026)
- [Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2606.10656/) (2026)
- [VGOcc: Learning Visual-Geometric Gaussians for Vision-Centric 3D Driving Occupancy Prediction](https://mlsanity.com/paper/2607.18078/) (2026)
- [ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes](https://mlsanity.com/paper/2605.09688/) (2026)
- [SpatialBench: Is Your Spatial Foundation Model an All-Round Player?](https://mlsanity.com/paper/2605.27367/) (2026)
- [FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views](https://mlsanity.com/paper/2605.29997/) (2026)
- [DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images](https://mlsanity.com/paper/2606.01315/) (2026)
- [L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction](https://mlsanity.com/paper/2606.29374/) (2026)
- [DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation](https://mlsanity.com/paper/2606.31488/) (2026)
- [RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction](https://mlsanity.com/paper/2607.23758/) (2026)
- [GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal](https://mlsanity.com/paper/2607.24024/) (2026)
- [USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes](https://mlsanity.com/paper/2608.19036/) (2026)
- [CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction](https://mlsanity.com/paper/2609.14521/) (2026)
- [CoCam4D: Geometry-Aware Cooperative 4D Perception for Camera-Only Autonomous Driving](https://mlsanity.com/paper/2610.11577/) (2026)
- [Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors](https://mlsanity.com/paper/2610.19201/) (2026)

## Abstract (arXiv)

Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows, making them slow and impractical. We revisit this problem from a feedforward perspective and introduce Driving Gaussian Grounded Transformer (DGGT), a unified framework for pose-free dynamic scene reconstruction. We note that the existing formulations, treating camera pose as a required input, limit flexibility and scalability. Instead, we reformulate pose as an output of the model, enabling reconstruction directly from sparse, unposed images and supporting an arbitrary number of views for long sequences. Our approach jointly predicts per-frame 3D Gaussian maps and camera parameters, disentangles dynamics with a lightweight dynamic head, and preserves temporal consistency with a lifespan head that modulates visibility over time. A diffusion-based rendering refinement further reduces motion/interpolation artifacts and improves novel-view quality under sparse inputs. The result is a single-pass, pose-free algorithm that achieves state-of-the-art performance and speed. Trained and evaluated on large-scale driving benchmarks (Waymo, nuScenes, Argoverse2), our method outperforms prior work both when trained on each dataset and in zero-shot transfer across datasets, and it scales well as the number of input frames increases.