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 2008.06520cs.CVcs.LG
收藏

用于形状生成的学习梯度场

Learning Gradient Fields for Shape Generation

Cornell University(康奈尔大学)

Ruojin Cai, Guandao Yang, Hadar Averbuch-Elor, Zekun Hao, Serge Belongie, Noah Snavely, Bharath Hariharan

摘要:

在这项工作中,我们提出了一种新的技术,从点云数据生成形状。点云可以被视为来自3D点分布的样本,其密度集中在形状的表面附近。因此,点云生成相当于将随机采样点移动到高密度区域。我们通过对未归一化的概率密度执行随机梯度上升来生成点云,从而将采样点移向高似然区域。我们的模型直接预测日志密度场的梯度,并且可以用从基于得分的生成模型适应的简单目标来训练。我们表明,我们的方法可以达到点云自动编码和生成的最先进的性能,同时也允许提取高质量的隐式曲面。代码可在https://github.com/RuojinCai/ShapeGF上获得。

英文摘要:

In this work, we propose a novel technique to generate shapes from point cloud data. A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape. Point cloud generation thus amounts to moving randomly sampled points to high-density areas. We generate point clouds by performing stochastic gradient ascent on an unnormalized probability density, thereby moving sampled points toward the high-likelihood regions. Our model directly predicts the gradient of the log density field and can be trained with a simple objective adapted from score-based generative models. We show that our method can reach state-of-the-art performance for point cloud auto-encoding and generation, while also allowing for extraction of a high-quality implicit surface. Code is available at https://github.com/RuojinCai/ShapeGF.

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。

↑