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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Wenhua, Wang, Qi, Wang, Guangming, Wang, Junping, Zhao, Tiankun, Liu, Yang, Gao, Dongchao, Liu, Zhe, Wang, Hesheng
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914718605639680
author Wu, Wenhua
Wang, Qi
Wang, Guangming
Wang, Junping
Zhao, Tiankun
Liu, Yang
Gao, Dongchao
Liu, Zhe
Wang, Hesheng
author_facet Wu, Wenhua
Wang, Qi
Wang, Guangming
Wang, Junping
Zhao, Tiankun
Liu, Yang
Gao, Dongchao
Liu, Zhe
Wang, Hesheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11789
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding
Wu, Wenhua
Wang, Qi
Wang, Guangming
Wang, Junping
Zhao, Tiankun
Liu, Yang
Gao, Dongchao
Liu, Zhe
Wang, Hesheng
Computer Vision and Pattern Recognition
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.
title EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.11789