# Multi-Level Neural Scene Graphs for Dynamic Urban Environments

arXiv: https://arxiv.org/abs/2404.00168 · HTML: https://mlsanity.com/paper/2404.00168/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 72 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 30 of 54)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [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)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video](https://mlsanity.com/paper/2012.12247/) (2020)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Space-time Neural Irradiance Fields for Free-Viewpoint Video](https://mlsanity.com/paper/2011.12950/) (2020)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)

## Built on by (most cited first, 27 of 27)

- [OmniRe: Omni Urban Scene Reconstruction](https://mlsanity.com/paper/2408.16760/) (2024)
- [STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes](https://mlsanity.com/paper/2501.00602/) (2024)
- [StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models](https://mlsanity.com/paper/2412.13188/) (2024)
- [Dynamic 3D Gaussian Fields for Urban Areas](https://mlsanity.com/paper/2406.03175/) (2024)
- [SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving](https://mlsanity.com/paper/2411.15482/) (2024)
- [Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset](https://mlsanity.com/paper/2406.09383/) (2024)
- [AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving](https://mlsanity.com/paper/2507.12137/) (2025)
- [EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting](https://mlsanity.com/paper/2411.15582/) (2024)
- [CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting](https://mlsanity.com/paper/2507.18473/) (2025)
- [Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streaming](https://mlsanity.com/paper/2503.08166/) (2025)
- [SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark](https://mlsanity.com/paper/2412.00730/) (2024)
- [ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking](https://mlsanity.com/paper/2601.01386/) (2026)
- [Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field](https://mlsanity.com/paper/2505.10049/) (2025)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [ArmGS: Composite Gaussian Appearance Refinement for Modeling Dynamic Urban Environments](https://mlsanity.com/paper/2507.03886/) (2025)
- [SaLF: Sparse Local Fields for Multi-Sensor Rendering in Real-Time](https://mlsanity.com/paper/2507.18713/) (2025)
- [Neural Atlas Graphs for Dynamic Scene Decomposition and Editing](https://mlsanity.com/paper/2509.16336/) (2025)
- [Visually-grounded Humanoid Agents](https://mlsanity.com/paper/2604.08509/) (2026)
- [sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views](https://mlsanity.com/paper/2502.04318/) (2025)
- [S3R-GS: Streamlining the Pipeline for Large-Scale Street Scene Reconstruction](https://mlsanity.com/paper/2503.08217/) (2025)
- [Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction](https://mlsanity.com/paper/2609.39960/) (2026)
- [UrbanCraft: Urban View Extrapolation via Hierarchical Sem-Geometric Priors](https://mlsanity.com/paper/2505.23434/) (2025)
- [Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering](https://mlsanity.com/paper/2510.13381/) (2025)
- [Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction](https://mlsanity.com/paper/2604.05908/) (2026)
- [SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation](https://mlsanity.com/paper/2606.03909/) (2026)
- [NoPA: Non-Parametric Online 3D Scene Graph Generation](https://mlsanity.com/paper/2607.00529/) (2026)
- [MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis](https://mlsanity.com/paper/2608.12442/) (2026)

## Abstract (arXiv)

We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures under varying environmental conditions. Previous works in this domain are either restricted to static environments, do not scale to more than a single short video, or struggle to separately represent dynamic object instances. To this end, we present a novel, decomposable radiance field approach for dynamic urban environments. We propose a multi-level neural scene graph representation that scales to thousands of images from dozens of sequences with hundreds of fast-moving objects. To enable efficient training and rendering of our representation, we develop a fast composite ray sampling and rendering scheme. To test our approach in urban driving scenarios, we introduce a new, novel view synthesis benchmark. We show that our approach outperforms prior art by a significant margin on both established and our proposed benchmark while being faster in training and rendering.