# EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding

arXiv: https://arxiv.org/abs/2403.11789 · HTML: https://mlsanity.com/paper/2403.11789/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 17 of 17)

- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Urban Radiance Fields](https://mlsanity.com/paper/2111.14643/) (2021)
- [SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction](https://mlsanity.com/paper/2212.00792/) (2022)
- [SPARF: Neural Radiance Fields from Sparse and Noisy Poses](https://mlsanity.com/paper/2211.11738/) (2022)
- [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](https://mlsanity.com/paper/2211.09869/) (2022)
- [A Survey of Structure from Motion](https://mlsanity.com/paper/1701.08493/) (2017)
- [SUDS: Scalable Urban Dynamic Scenes](https://mlsanity.com/paper/2303.14536/) (2023)
- [Progressively Optimized Local Radiance Fields for Robust View Synthesis](https://mlsanity.com/paper/2303.13791/) (2023)
- [PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction](https://mlsanity.com/paper/2302.10668/) (2023)
- [READ: Large-Scale Neural Scene Rendering for Autonomous Driving](https://mlsanity.com/paper/2205.05509/) (2022)
- [Road surface 3d reconstruction based on dense subpixel disparity map estimation](https://mlsanity.com/paper/1807.01874/) (2018)
- [Rethinking Road Surface 3D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation](https://mlsanity.com/paper/2012.10802/) (2020)
- [GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images](https://mlsanity.com/paper/2303.13777/) (2023)
- [ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction](https://mlsanity.com/paper/2212.04096/) (2022)
- [RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation](https://mlsanity.com/paper/2306.11368/) (2023)
- [ABLE-NeRF: Attention-Based Rendering with Learnable Embeddings for Neural Radiance Field](https://mlsanity.com/paper/2303.13817/) (2023)

## Built on by (most cited first, 13 of 13)

- [Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2503.14537/) (2025)
- [RoadBEV: Road Surface Reconstruction in Bird's Eye View](https://mlsanity.com/paper/2404.06605/) (2024)
- [RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian](https://mlsanity.com/paper/2405.14342/) (2024)
- [PseudoMapTrainer: Learning Online Mapping without HD Maps](https://mlsanity.com/paper/2508.18788/) (2025)
- [Generalizable Prompt Learning of CLIP: A Brief Overview](https://mlsanity.com/paper/2503.01263/) (2025)
- [Shape Your Ground: Refining Road Surfaces Beyond Planar Representations](https://mlsanity.com/paper/2504.16103/) (2025)
- [Enhancing Target-unspecific Tasks through a Features Matrix](https://mlsanity.com/paper/2505.03414/) (2025)
- [MapRF: Weakly Supervised Online HD Map Construction via NeRF-Guided Self-Training](https://mlsanity.com/paper/2511.19527/) (2025)
- [WeatherCity: Urban Scene Reconstruction with Controllable Multi-Weather Transformation](https://mlsanity.com/paper/2602.22096/) (2026)
- [Establishing Reality-Virtuality Interconnections in Urban Digital Twins for Superior Intelligent Road Inspection and Simulation](https://mlsanity.com/paper/2412.17699/) (2024)
- [MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenes](https://mlsanity.com/paper/2510.15467/) (2025)
- [RoGS: Adaptive Meshgrid Gaussian for Large-Scale Road Surface Mapping](https://mlsanity.com/paper/2607.15048/) (2026)
- [RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction](https://mlsanity.com/paper/2607.23758/) (2026)

## Abstract (arXiv)

Road surface reconstruction plays a vital role in autonomous driving systems, enabling road lane perception and high-precision mapping. Recently, neural implicit encoding has achieved remarkable results in scene representation, particularly in the realistic rendering of scene textures. However, it faces challenges in directly representing geometric information for large-scale scenes. To address this, we propose EMIE-MAP, a novel method for large-scale road surface reconstruction based on explicit mesh and implicit encoding. The road geometry is represented using explicit mesh, where each vertex stores implicit encoding representing the color and semantic information. To overcome the difficulty in optimizing road elevation, we introduce a trajectory-based elevation initialization and an elevation residual learning method based on Multi-Layer Perceptron (MLP). Additionally, by employing implicit encoding and multi-camera color MLPs decoding, we achieve separate modeling of scene physical properties and camera characteristics, allowing surround-view reconstruction compatible with different camera models. Our method achieves remarkable road surface reconstruction performance in a variety of real-world challenging scenarios.