Guardado en:
Detalles Bibliográficos
Autores principales: Fang, Zheng, Ye, Ke, Liu, Yaofang, Li, Gongzhe, Zhao, Xianhong, Li, Jialong, Wang, Ruxin, Zhang, Yuchen, Ji, Xiangyang, Sun, Qilin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2412.11680
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917870100807680
author Fang, Zheng
Ye, Ke
Liu, Yaofang
Li, Gongzhe
Zhao, Xianhong
Li, Jialong
Wang, Ruxin
Zhang, Yuchen
Ji, Xiangyang
Sun, Qilin
author_facet Fang, Zheng
Ye, Ke
Liu, Yaofang
Li, Gongzhe
Zhao, Xianhong
Li, Jialong
Wang, Ruxin
Zhang, Yuchen
Ji, Xiangyang
Sun, Qilin
contents Point clouds or depth images captured by current RGB-D cameras often suffer from low resolution, rendering them insufficient for applications such as 3D reconstruction and robots. Existing point cloud super-resolution (PCSR) methods are either constrained by geometric artifacts or lack attention to edge details. To address these issues, we propose an edge-guided geometric-preserving 3D point cloud super-resolution (EGP3D) method tailored for RGB-D cameras. Our approach innovatively optimizes the point cloud with an edge constraint on a projected 2D space, thereby ensuring high-quality edge preservation in the 3D PCSR task. To tackle geometric optimization challenges in super-resolution point clouds, particularly preserving edge shapes and smoothness, we introduce a multi-faceted loss function that simultaneously optimizes the Chamfer distance, Hausdorff distance, and gradient smoothness. Existing datasets used for point cloud upsampling are predominantly synthetic and inadequately represent real-world scenarios, neglecting noise and stray light effects. To address the scarcity of realistic RGB-D data for PCSR tasks, we built a dataset that captures real-world noise and stray-light effects, offering a more accurate representation of authentic environments. Validated through simulations and real-world experiments, the proposed method exhibited superior performance in preserving edge clarity and geometric details.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11680
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera
Fang, Zheng
Ye, Ke
Liu, Yaofang
Li, Gongzhe
Zhao, Xianhong
Li, Jialong
Wang, Ruxin
Zhang, Yuchen
Ji, Xiangyang
Sun, Qilin
Computer Vision and Pattern Recognition
Point clouds or depth images captured by current RGB-D cameras often suffer from low resolution, rendering them insufficient for applications such as 3D reconstruction and robots. Existing point cloud super-resolution (PCSR) methods are either constrained by geometric artifacts or lack attention to edge details. To address these issues, we propose an edge-guided geometric-preserving 3D point cloud super-resolution (EGP3D) method tailored for RGB-D cameras. Our approach innovatively optimizes the point cloud with an edge constraint on a projected 2D space, thereby ensuring high-quality edge preservation in the 3D PCSR task. To tackle geometric optimization challenges in super-resolution point clouds, particularly preserving edge shapes and smoothness, we introduce a multi-faceted loss function that simultaneously optimizes the Chamfer distance, Hausdorff distance, and gradient smoothness. Existing datasets used for point cloud upsampling are predominantly synthetic and inadequately represent real-world scenarios, neglecting noise and stray light effects. To address the scarcity of realistic RGB-D data for PCSR tasks, we built a dataset that captures real-world noise and stray-light effects, offering a more accurate representation of authentic environments. Validated through simulations and real-world experiments, the proposed method exhibited superior performance in preserving edge clarity and geometric details.
title EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11680