SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Lizhe, Wang, Bohua, Xie, Hongwei, Liu, Daqi, Liu, Li, Tian, Zhiqiang, Yang, Kuiyuan, Wang, Bing
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929284682088448
author Liu, Lizhe
Wang, Bohua
Xie, Hongwei
Liu, Daqi
Liu, Li
Tian, Zhiqiang
Yang, Kuiyuan
Wang, Bing
author_facet Liu, Lizhe
Wang, Bohua
Xie, Hongwei
Liu, Daqi
Liu, Li
Tian, Zhiqiang
Yang, Kuiyuan
Wang, Bing
contents Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems. Recently, object-free methods have attracted considerable attention. Such methods perceive the world by predicting the semantics of discrete voxel grids but fail to construct continuous and accurate obstacle surfaces. To this end, in this paper, we propose SurroundSDF to implicitly predict the signed distance field (SDF) and semantic field for the continuous perception from surround images. Specifically, we introduce a query-based approach and utilize SDF constrained by the Eikonal formulation to accurately describe the surfaces of obstacles. Furthermore, considering the absence of precise SDF ground truth, we propose a novel weakly supervised paradigm for SDF, referred to as the Sandwich Eikonal formulation, which emphasizes applying correct and dense constraints on both sides of the surface, thereby enhancing the perceptual accuracy of the surface. Experiments suggest that our method achieves SOTA for both occupancy prediction and 3D scene reconstruction tasks on the nuScenes dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14366
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
Liu, Lizhe
Wang, Bohua
Xie, Hongwei
Liu, Daqi
Liu, Li
Tian, Zhiqiang
Yang, Kuiyuan
Wang, Bing
Computer Vision and Pattern Recognition
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems. Recently, object-free methods have attracted considerable attention. Such methods perceive the world by predicting the semantics of discrete voxel grids but fail to construct continuous and accurate obstacle surfaces. To this end, in this paper, we propose SurroundSDF to implicitly predict the signed distance field (SDF) and semantic field for the continuous perception from surround images. Specifically, we introduce a query-based approach and utilize SDF constrained by the Eikonal formulation to accurately describe the surfaces of obstacles. Furthermore, considering the absence of precise SDF ground truth, we propose a novel weakly supervised paradigm for SDF, referred to as the Sandwich Eikonal formulation, which emphasizes applying correct and dense constraints on both sides of the surface, thereby enhancing the perceptual accuracy of the surface. Experiments suggest that our method achieves SOTA for both occupancy prediction and 3D scene reconstruction tasks on the nuScenes dataset.
title SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.14366