arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.01529cs.CV
收藏

IterativePFN:真正的迭代式点云滤波

IterativePFN: True Iterative Point Cloud Filtering

Deakin University(迪肯大学);China University of Mining and Technology(中国矿业大学);Defense Science and Technology Group(澳大利亚国防科学技术集团);Nanyang Technological University(南洋理工大学)

Dasith de Silva Edirimuni, Xuequan Lu, Zhiwen Shao, Gang Li, Antonio Robles-Kelly, Ying He

AI总结:

针对现有基于学习的点云滤波方法迭代仅在测试时进行、收敛慢的问题,提出内置多迭代模块、采用自适应真实标签损失训练的IterativePFN,实现真正的迭代滤波,性能优于现有最优方法。

摘要:

点云的质量通常受采集过程中引入的噪声限制。因此,一项基础的3D视觉任务是去除噪声,即点云滤波或去噪。当前最优的基于学习的方法聚焦于训练神经网络以推断滤波后的位移,并将噪声点直接移动到潜在的干净表面上。在高噪声条件下,这些方法会迭代执行滤波过程。然而,这种迭代滤波仅在测试阶段进行,在确保点快速收敛到干净表面方面效果较差。我们提出IterativePFN(迭代点云滤波网络),它由多个IterationModule(迭代模块)组成,在单个网络内部对真正的迭代滤波过程进行建模。我们使用一种新颖的损失函数训练IterativePFN网络,该损失函数在每次迭代中采用自适应的真实标签目标,以捕捉训练过程中间滤波结果之间的关系,这确保了滤波结果能更快收敛到干净表面。与现有最优方法相比,我们的方法能够取得更优的性能。源代码可在以下地址获取:https://github.com/ddsediri/IterativePFN。

英文摘要:

The quality of point clouds is often limited by noise introduced during their capture process. Consequently, a fundamental 3D vision task is the removal of noise, known as point cloud filtering or denoising. State-of-the-art learning based methods focus on training neural networks to infer filtered displacements and directly shift noisy points onto the underlying clean surfaces. In high noise conditions, they iterate the filtering process. However, this iterative filtering is only done at test time and is less effective at ensuring points converge quickly onto the clean surfaces. We propose IterativePFN (iterative point cloud filtering network), which consists of multiple IterationModules that model the true iterative filtering process internally, within a single network. We train our IterativePFN network using a novel loss function that utilizes an adaptive ground truth target at each iteration to capture the relationship between intermediate filtering results during training. This ensures that the filtered results converge faster to the clean surfaces. Our method is able to obtain better performance compared to state-of-the-art methods. The source code can be found at: https://github.com/ddsediri/IterativePFN.

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。

↑