arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.08435cs.CV
收藏

DiFT:多视图立体视觉的可微差分特征变换

DiFT: Differentiable Differential Feature Transform for Multi-View Stereo

Zhejiang University(浙江大学)

Kaizhang Kang, Chong Zeng, Hongzhi Wu, Kun Zhou

摘要:

我们提出了一个新的框架,自动学习转换的差分线索从一堆图像密集捕获的旋转运动到空间歧视和视图不变的每像素功能,在每个视图。这些低级特征可以被直接馈送到任何现有的多视图立体视觉技术以用于增强的3D重建。采集期间的照明条件也可以以可区分的方式联合优化。我们从十几个预扫描的物体中取样,这些物体具有各种各样的几何形状和反射率,以合成大量高质量的训练数据。我们的功能的有效性证明了一些具有挑战性的对象与lightstage收购,比较有利的国家的最先进的技术。最后,我们探讨了几何细节可视化和复杂外观的计算风格化的其他应用。

英文摘要:

We present a novel framework to automatically learn to transform the differential cues from a stack of images densely captured with a rotational motion into spatially discriminative and view-invariant per-pixel features at each view. These low-level features can be directly fed to any existing multi-view stereo technique for enhanced 3D reconstruction. The lighting condition during acquisition can also be jointly optimized in a differentiable fashion. We sample from a dozen of pre-scanned objects with a wide variety of geometry and reflectance to synthesize a large amount of high-quality training data. The effectiveness of our features is demonstrated on a number of challenging objects acquired with a lightstage, comparing favorably with state-of-the-art techniques. Finally, we explore additional applications of geometric detail visualization and computational stylization of complex appearance.

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。

↑