# DVGT: Driving Visual Geometry Transformer

arXiv: https://arxiv.org/abs/2512.16919 · HTML: https://mlsanity.com/paper/2512.16919/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 71 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 30 of 62)

- [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)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [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)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image](https://mlsanity.com/paper/2307.10984/) (2023)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [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)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [Query-Key Normalization for Transformers](https://mlsanity.com/paper/2010.04245/) (2020)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)

## Built on by (most cited first, 21 of 21)

- [DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale](https://mlsanity.com/paper/2604.00813/) (2026)
- [Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation](https://mlsanity.com/paper/2604.18486/) (2026)
- [VG3S: Visual Geometry Grounded Gaussian Splatting for Semantic Occupancy Prediction](https://mlsanity.com/paper/2603.06210/) (2026)
- [SM4RT: Learning Structured Motion Geometry for 4D Reconstruction](https://mlsanity.com/paper/2607.22534/) (2026)
- [GeoWAM: Visual Geometry World Action Models for Autonomous Driving](https://mlsanity.com/paper/2608.23486/) (2026)
- [FlexMap: Robust HD Map Construction under Flexible Camera Configurations](https://mlsanity.com/paper/2601.22376/) (2026)
- [Geometry-Grounded Unified 3D Perception for Autonomous Driving](https://mlsanity.com/paper/2608.13147/) (2026)
- [IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation](https://mlsanity.com/paper/2605.16258/) (2026)
- [Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning](https://mlsanity.com/paper/2606.01935/) (2026)
- [SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving](https://mlsanity.com/paper/2606.16960/) (2026)
- [Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers](https://mlsanity.com/paper/2605.23892/) (2026)
- [FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views](https://mlsanity.com/paper/2605.29997/) (2026)
- [LiAuto-GeoX: Efficient Grounded Driving Transformer](https://mlsanity.com/paper/2606.05774/) (2026)
- [DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation](https://mlsanity.com/paper/2606.31488/) (2026)
- [SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Prediction](https://mlsanity.com/paper/2607.04732/) (2026)
- [TRIG: Trajectory-Rig Decoupled Metric Geometry Learning](https://mlsanity.com/paper/2607.05801/) (2026)
- [TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval](https://mlsanity.com/paper/2608.13495/) (2026)
- [GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation](https://mlsanity.com/paper/2608.16234/) (2026)
- [FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry](https://mlsanity.com/paper/2609.13733/) (2026)
- [PhysWAM: Physically Consistent World Action Model for Autonomous Driving](https://mlsanity.com/paper/2609.37970/) (2026)
- [Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving](https://mlsanity.com/paper/2610.15112/) (2026)

## Abstract (arXiv)

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera configurations. To bridge this gap, we propose a Driving Visual Geometry Transformer (DVGT), which reconstructs a global dense 3D point map from a sequence of unposed multi-view visual inputs. We first extract visual features for each image using a DINO backbone, and employ alternating intra-view local attention, cross-view spatial attention, and cross-frame temporal attention to infer geometric relations across images. We then use multiple heads to decode a global point map in the ego coordinate of the first frame and the ego poses for each frame. Unlike conventional methods that rely on precise camera parameters, DVGT is free of explicit 3D geometric priors, enabling flexible processing of arbitrary camera configurations. DVGT directly predicts metric-scaled geometry from image sequences, eliminating the need for post-alignment with external sensors. Trained on a large mixture of driving datasets including nuScenes, OpenScene, Waymo, KITTI, and DDAD, DVGT significantly outperforms existing models on various scenarios. Code is available at https://github.com/wzzheng/DVGT.