NeRO: Neural Road Surface Reconstruction
Not on the map. Why?
Abstract (arXiv)
Accurately reconstructing road surfaces is pivotal for various applications especially in autonomous driving. This paper introduces a position encoding Multi-Layer Perceptrons (MLPs) framework to reconstruct road surfaces, with input as world coordinates x and y, and output as height, color, and semantic information. The effectiveness of this method is demonstrated through its compatibility with a variety of road height sources like vehicle camera poses, LiDAR point clouds, and SFM point clouds, robust to the semantic noise of images like sparse labels and noise semantic prediction, and fast training speed, which indicates a promising application for rendering road surfaces with semantics, particularly in applications demanding visualization of road surface, 4D labeling, and semantic groupings.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 36 references that are in the map. First posted on arXiv 17 May 2024.
Builds on
29 of 36 references.
References · 29
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
- 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
- 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
17 more
- 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
- 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
- 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 415
- 2021Urban Radiance Fieldscited by 263
- 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
- 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
- 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
- 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
- 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
- 2019Planar Prior Assisted PatchMatch Multi-View Stereocited by 57
- 2022READ: Large-Scale Neural Scene Rendering for Autonomous Drivingcited by 51
- 2021RoadMap: A Light-Weight Semantic Map for Visual Localization towards Autonomous Drivingcited by 34
- 2023RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representationcited by 20
- 2023MV-Map: Offboard HD-Map Generation with Multi-view Consistencycited by 19
- 2021PHI-MVS: Plane Hypothesis Inference Multi-view Stereo for Large-Scale Scene Reconstructioncited by 8
- 2023PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Scene Reconstructioncited by 8
- 2024Semantic Is Enough: Only Semantic Information For NeRF Reconstructioncited by 5
Built on by
Citing papers per year: 2025: 1.
1 paper.