# Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving

arXiv: https://arxiv.org/abs/2412.06777 · HTML: https://mlsanity.com/paper/2412.06777/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 56 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Builds on (most cited first, 12 of 12)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation](https://mlsanity.com/paper/2204.03636/) (2022)
- [DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos](https://mlsanity.com/paper/2405.02280/) (2024)
- [Image2Mesh: A Learning Framework for Single Image 3D Reconstruction](https://mlsanity.com/paper/1711.10669/) (2017)
- [PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views](https://mlsanity.com/paper/2410.18979/) (2024)

## Built on by (most cited first, 29 of 29)

- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling](https://mlsanity.com/paper/2507.07982/) (2025)
- [Doe-1: Closed-Loop Autonomous Driving with Large World Model](https://mlsanity.com/paper/2412.09627/) (2024)
- [LONG3R: Long Sequence Streaming 3D Reconstruction](https://mlsanity.com/paper/2507.18255/) (2025)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [DVGT: Driving Visual Geometry Transformer](https://mlsanity.com/paper/2512.16919/) (2025)
- [AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend](https://mlsanity.com/paper/2511.20343/) (2025)
- [DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion](https://mlsanity.com/paper/2510.15264/) (2025)
- [DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale](https://mlsanity.com/paper/2604.00813/) (2026)
- [Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT](https://mlsanity.com/paper/2507.08448/) (2025)
- [E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models](https://mlsanity.com/paper/2506.01933/) (2025)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction](https://mlsanity.com/paper/2506.23863/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving](https://mlsanity.com/paper/2511.22264/) (2025)
- [Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2508.07908/) (2025)
- [EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis](https://mlsanity.com/paper/2601.15951/) (2026)
- [SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes](https://mlsanity.com/paper/2603.22893/) (2026)
- [Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving](https://mlsanity.com/paper/2605.22809/) (2026)
- [DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes](https://mlsanity.com/paper/2510.24734/) (2025)
- [XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method](https://mlsanity.com/paper/2510.07856/) (2025)
- [CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation](https://mlsanity.com/paper/2511.16428/) (2025)
- [Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2606.10656/) (2026)
- [SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving](https://mlsanity.com/paper/2606.16960/) (2026)
- [Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes](https://mlsanity.com/paper/2606.30047/) (2026)
- [TRIG: Trajectory-Rig Decoupled Metric Geometry Learning](https://mlsanity.com/paper/2607.05801/) (2026)
- [CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth Estimation](https://mlsanity.com/paper/2609.05397/) (2026)
- [AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend](https://mlsanity.com/paper/2609.19518/) (2026)
- [VDGS: Visibility-Driven Large-Scale 3D Gaussian Splatting for Aerial Scene Reconstruction](https://mlsanity.com/paper/2609.23049/) (2026)

## Abstract (arXiv)

Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose Driv3R, a DUSt3R-based framework that directly regresses per-frame point maps from multi-view image sequences. To achieve streaming dense reconstruction, we maintain a memory pool to reason both spatial relationships across sensors and dynamic temporal contexts to enhance multi-view 3D consistency and temporal integration. Furthermore, we employ a 4D flow predictor to identify moving objects within the scene to direct our network focus more on reconstructing these dynamic regions. Finally, we align all per-frame pointmaps consistently to the world coordinate system in an optimization-free manner. We conduct extensive experiments on the large-scale nuScenes dataset to evaluate the effectiveness of our method. Driv3R outperforms previous frameworks in 4D dynamic scene reconstruction, achieving 15x faster inference speed compared to methods requiring global alignment. Code: https://github.com/Barrybarry-Smith/Driv3R.