arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.06112cs.CV
收藏

CU-Net:点云的实时的高保真彩色上采样

CU-Net: Real-Time High-Fidelity Color Upsampling for Point Clouds

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);New Jersey Institute of Technology(新泽西理工学院)

Lingdong Wang, Mohammad Hajiesmaili, Jacob Chakareski, Ramesh K. Sitaraman

摘要:

由于现有技术的捕获、处理和通信限制,点云上采样对于高质量增强现实、虚拟现实和远程呈现应用是必不可少的。虽然已经很好地研究了几何上采样以致密点云的坐标,但是颜色属性的上采样在很大程度上被忽略了。在本文中,我们提出了CU-Net,这是第一个深度学习点云颜色上采样模型,可以实现低延迟和高视觉保真度操作。CU-Net通过利用基于稀疏卷积的特征提取器和基于神经隐函数的颜色预测模块实现线性时间和空间复杂度。因此,CU-Net在理论上保证比大多数具有二次复杂度的现有方法更有效。实验结果表明,CU-Net能够实时的对近百万点的真实感点云进行着色,且具有明显优于基线的视觉效果。此外,CU-Net可以适应任意上采样率和不可见对象,无需重新训练。我们的源代码可在https://github.com/UMass-LIDS/cunet上获得。

英文摘要:

Point cloud upsampling is essential for high-quality augmented reality, virtual reality, and telepresence applications, due to the capture, processing, and communication limitations of existing technologies. Although geometry upsampling to densify a point cloud's coordinates has been well studied, the upsampling of the color attributes has been largely overlooked. In this paper, we propose CU-Net, the first deep-learning point cloud color upsampling model that enables low latency and high visual fidelity operation. CU-Net achieves linear time and space complexity by leveraging a feature extractor based on sparse convolution and a color prediction module based on neural implicit function. Therefore, CU-Net is theoretically guaranteed to be more efficient than most existing methods with quadratic complexity. Experimental results demonstrate that CU-Net can colorize a photo-realistic point cloud with nearly a million points in real time, while having notably better visual performance than baselines. Besides, CU-Net can adapt to arbitrary upsampling ratios and unseen objects without retraining. Our source code is available at https://github.com/UMass-LIDS/cunet.

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。

↑