# ViiNeuS: Volumetric Initialization for Implicit Neural Surface reconstruction of urban scenes with limited image overlap

arXiv: https://arxiv.org/abs/2403.10344 · HTML: https://mlsanity.com/paper/2403.10344/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 15 Mar 2024.

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

- [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)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://mlsanity.com/paper/2212.05231/) (2022)
- [Urban Radiance Fields](https://mlsanity.com/paper/2111.14643/) (2021)
- [PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving](https://mlsanity.com/paper/2112.12610/) (2021)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance](https://mlsanity.com/paper/2312.00846/) (2023)
- [StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views](https://mlsanity.com/paper/2306.04988/) (2023)
- [Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement](https://mlsanity.com/paper/2303.02091/) (2023)
- [Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes](https://mlsanity.com/paper/2304.03266/) (2023)
- [NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation](https://mlsanity.com/paper/2303.17147/) (2023)
- [Adaptive Shells for Efficient Neural Radiance Field Rendering](https://mlsanity.com/paper/2311.10091/) (2023)
- [I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs](https://mlsanity.com/paper/2303.07634/) (2023)
- [RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials](https://mlsanity.com/paper/1901.01535/) (2019)
- [VMesh: Hybrid Volume-Mesh Representation for Efficient View Synthesis](https://mlsanity.com/paper/2303.16184/) (2023)
- [MOISST: Multimodal Optimization of Implicit Scene for SpatioTemporal calibration](https://mlsanity.com/paper/2303.03056/) (2023)
- [Sur2f: A Hybrid Representation for High-Quality and Efficient Surface Reconstruction from Multi-view Images](https://mlsanity.com/paper/2401.03704/) (2024)
- [3D Surface Reconstruction from Voxel-based Lidar Data](https://mlsanity.com/paper/1906.10515/) (2019)

## Built on by (most cited first, 4 of 4)

- [Refining Ground Truth Poses in Autonomous Driving Datasets via Neural Rendering](https://mlsanity.com/paper/2504.15776/) (2025)
- [J-NeuS: Joint field optimization for Neural Surface reconstruction in urban scenes with limited image overlap](https://mlsanity.com/paper/2501.03932/) (2025)
- [Multiscale Corrections by Continuous Super-Resolution](https://mlsanity.com/paper/2411.07576/) (2024)
- [DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction](https://mlsanity.com/paper/2606.23031/) (2026)

## Abstract (arXiv)

Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct driving scenes due to their large size, highly complex nature and their limited visual observation overlap. Hence, to achieve accurate reconstructions, additional supervision data such as LiDAR, strong geometric priors, and long training times are required. To tackle such limitations, we present ViiNeuS, a new hybrid implicit surface learning method that efficiently initializes the signed distance field to reconstruct large driving scenes from 2D street view images. ViiNeuS's hybrid architecture models two separate implicit fields: one representing the volumetric density of the scene, and another one representing the signed distance to the surface. To accurately reconstruct urban outdoor driving scenarios, we introduce a novel volume-rendering strategy that relies on self-supervised probabilistic density estimation to sample points near the surface and transition progressively from volumetric to surface representation. Our solution permits a proper and fast initialization of the signed distance field without relying on any geometric prior on the scene, compared to concurrent methods. By conducting extensive experiments on four outdoor driving datasets, we show that ViiNeuS can learn an accurate and detailed 3D surface representation of various urban scene while being two times faster to train compared to previous state-of-the-art solutions.