arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07685cs.CVcs.AI
收藏

基于单幅图像的视觉增强三维点云重建

Visual Enhanced 3D Point Cloud Reconstruction from A Single Image

Nanyang Technological University(南洋理工大学)

Guiju Ping, Mahdi Abolfazli Esfahani, Han Wang

摘要:

解决从单个图像进行3D对象重建的挑战性问题适当地给予现有技术利用单个单目相机而不是需要深度传感器来执行的能力。近年来,由于深度学习的发展,单个图像的3D重建已经展示了令人印象深刻的进展。现有的研究多采用倒角距离作为损失函数来指导神经网络的训练。但是,倒角损失将为3D点云中的所有点提供相等的权重。它倾向于牺牲细粒度和薄结构,以避免招致高损失,这将导致视觉上不满意的结果。本文提出了一个框架,可以恢复一个详细的三维点云从一个单一的图像,重点放在边界(边缘和角点)。实验结果表明,该方法在定性和定量上都明显优于现有技术,并且具有更少的训练参数。

英文摘要:

Solving the challenging problem of 3D object reconstruction from a single image appropriately gives existing technologies the ability to perform with a single monocular camera rather than requiring depth sensors. In recent years, thanks to the development of deep learning, 3D reconstruction of a single image has demonstrated impressive progress. Existing researches use Chamfer distance as a loss function to guide the training of the neural network. However, the Chamfer loss will give equal weights to all points inside the 3D point clouds. It tends to sacrifice fine-grained and thin structures to avoid incurring a high loss, which will lead to visually unsatisfactory results. This paper proposes a framework that can recover a detailed three-dimensional point cloud from a single image by focusing more on boundaries (edge and corner points). Experimental results demonstrate that the proposed method outperforms existing techniques significantly, both qualitatively and quantitatively, and has fewer training parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑