# DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction

arXiv: https://arxiv.org/abs/2606.23031 · HTML: https://mlsanity.com/paper/2606.23031/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 31 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)
- [GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2311.11700/) (2023)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving](https://mlsanity.com/paper/2112.12610/) (2021)
- [OmniRe: Omni Urban Scene Reconstruction](https://mlsanity.com/paper/2408.16760/) (2024)
- [NeuRAD: Neural Rendering for Autonomous Driving](https://mlsanity.com/paper/2311.15260/) (2023)
- [Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering](https://mlsanity.com/paper/2311.18561/) (2023)
- [StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views](https://mlsanity.com/paper/2306.04988/) (2023)
- [Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering](https://mlsanity.com/paper/2412.04459/) (2024)
- [GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction](https://mlsanity.com/paper/2509.18090/) (2025)
- [SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization](https://mlsanity.com/paper/2407.12667/) (2024)
- [ViiNeuS: Volumetric Initialization for Implicit Neural Surface reconstruction of urban scenes with limited image overlap](https://mlsanity.com/paper/2403.10344/) (2024)
- [Refining Ground Truth Poses in Autonomous Driving Datasets via Neural Rendering](https://mlsanity.com/paper/2504.15776/) (2025)
- [SaLF: Sparse Local Fields for Multi-Sensor Rendering in Real-Time](https://mlsanity.com/paper/2507.18713/) (2025)
- [J-NeuS: Joint field optimization for Neural Surface reconstruction in urban scenes with limited image overlap](https://mlsanity.com/paper/2501.03932/) (2025)
- [SVRecon: Sparse Voxel Rasterization for Surface Reconstruction](https://mlsanity.com/paper/2511.17364/) (2025)
- [LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2604.01388/) (2026)

## Abstract (arXiv)

Reconstructing dynamic urban scenes remains challenging due to the unbounded nature of driving environments and the presence of multiple dynamic objects. Currently, potentially faster sparse voxel methods are mainly designed for static scenarios. On the other hand, dynamic approaches based on 3D Gaussian Splatting, despite their high-fidelity, are often time-consuming for driving scenarios and exhibit uncontrollable memory growth in large scenes. To address these limitations, we present DrivingVoxels, a compositional sparse voxel rendering framework for dynamic driving scenes. Our method jointly rasterizes sparse voxels from multiple independent octrees within a single rendering pass. Each rigid dynamic object is represented by an octree defined in its local coordinate frame, while a separate static octree models the stationary background. DrivingVoxels adopts a fully explicit, neural-free representation together with a LiDAR-guided structural initialization that efficiently captures scene geometry. We evaluate our framework on the PandaSet benchmark, demonstrating that DrivingVoxels performs on par on perceptual metrics and better on structural metrics for NVS and reconstruction while requiring shorter training times than previous 3DGS-base methods to an efficient optimization workflow anchored by a strong LiDAR prior.