# Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving

arXiv: https://arxiv.org/abs/2610.15112 · HTML: https://mlsanity.com/paper/2610.15112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Generative simulation for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 31 of its 34 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Placed in

- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)

## Builds on (most cited first, 30 of 31)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [NeuRAD: Neural Rendering for Autonomous Driving](https://mlsanity.com/paper/2311.15260/) (2023)
- [MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds](https://mlsanity.com/paper/2412.06974/) (2024)
- [TTT3R: 3D Reconstruction as Test-Time Training](https://mlsanity.com/paper/2509.26645/) (2025)
- [VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences](https://mlsanity.com/paper/2507.16443/) (2025)
- [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025)
- [InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams](https://mlsanity.com/paper/2601.02281/) (2026)
- [End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotation](https://mlsanity.com/paper/2406.17680/) (2024)
- [LongStream: Long-Sequence Streaming Autoregressive Visual Geometry](https://mlsanity.com/paper/2602.13172/) (2026)
- [DVGT: Driving Visual Geometry Transformer](https://mlsanity.com/paper/2512.16919/) (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)
- [UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction](https://mlsanity.com/paper/2511.04595/) (2025)
- [ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction](https://mlsanity.com/paper/2603.07552/) (2026)
- [OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models](https://mlsanity.com/paper/2604.17915/) (2026)

## Abstract (arXiv)

High-fidelity closed-loop simulation for autonomous driving increasingly relies on dense multi-view 3D reconstruction. While recent feed-forward geometric foundation models have revolutionized per-scene optimization, applying them to continuous, long-horizon driving sequences is computationally intractable due to GPU memory limits and the quadratic complexity of global attention. Existing scaling strategies are fundamentally limited, as causal streaming suffers from compounding scale drift and trajectory deviation, while rigid "chunk-then-align" heuristics fragment global context and produce trajectory discontinuities. To address these limitations, we introduce Drive3R, a block-wise streaming geometric foundation model. Its block-wise causal attention resolves the scalability bottleneck of fully bidirectional attention while avoiding the loss of local future context in purely causal streaming. Its confidence-aware re-anchoring further mitigates long-range drift by detecting unreliable streaming states, re-initializing the KV cache, and stitching refreshed segments through SE(3) alignment. Extensive experiments demonstrate that Drive3R establishes a new state-of-the-art on nuScenes, KITTI, and Waymo. Specifically, on nuScenes, it improves over the recent DVGT-2 baseline from 0.1806 to 0.1081 in AbsRel, from 0.6750 to 0.5344 in point-cloud Accuracy, and from 1.5812 to 0.9092 in ATE.