arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.16482cs.CV
收藏

Point2Pix:基于神经辐射场的真实感点云绘制

Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields

The Chinese University of Hong Kong(香港中文大学);SmartMore(思谋科技)

Tao Hu, Xiaogang Xu, Shu Liu, Jiaya Jia

摘要:

由于点云表示的稀疏性,从点云合成照片级真实感图像是具有挑战性的。最近提出的神经辐射场和扩展用于从2D输入合成逼真的图像。在本文中,我们提出了Point2Pix作为一种新的点渲染器连接的3D稀疏点云与2D密集的图像像素。利用点云3D先验和NeRF渲染管道,我们的方法可以从彩色点云合成高质量的图像,通常用于新颖的室内场景。为了提高射线采样的效率,我们提出了点引导采样,它侧重于有效样本。此外,我们提出了点编码来构建多尺度辐射场,提供有区别的3D点特征。最后,我们提出了融合编码,以有效地合成高质量的图像。在ScanNet和ArkitScenes数据集上的大量实验证明了该方法的有效性和推广性。

英文摘要:

Synthesizing photo-realistic images from a point cloud is challenging because of the sparsity of point cloud representation. Recent Neural Radiance Fields and extensions are proposed to synthesize realistic images from 2D input. In this paper, we present Point2Pix as a novel point renderer to link the 3D sparse point clouds with 2D dense image pixels. Taking advantage of the point cloud 3D prior and NeRF rendering pipeline, our method can synthesize high-quality images from colored point clouds, generally for novel indoor scenes. To improve the efficiency of ray sampling, we propose point-guided sampling, which focuses on valid samples. Also, we present Point Encoding to build Multi-scale Radiance Fields that provide discriminative 3D point features. Finally, we propose Fusion Encoding to efficiently synthesize high-quality images. Extensive experiments on the ScanNet and ArkitScenes datasets demonstrate the effectiveness and generalization.

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。

↑