arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.15021cs.CV
收藏

一致性视频深度估计

Consistent Video Depth Estimation

University of Washington(华盛顿大学);Virginia Tech(弗吉尼亚理工大学);Facebook(脸书)

Xuan Luo, Jia-Bin Huang, Richard Szeliski, Kevin Matzen, Johannes Kopf

摘要:

我们提出了一种算法重建密集的,几何一致的深度为所有像素在单目视频。我们利用传统的结构从运动重建建立视频中的像素的几何约束。与经典重建中的ad-hoc先验不同,我们使用基于学习的先验,即,卷积神经网络训练用于单图像深度估计。在测试时,我们对该网络进行微调,以满足特定输入视频的几何约束,同时保留其在受约束较少的视频部分中合成合理深度细节的能力。我们通过定量验证表明,我们的方法实现了更高的精度和更高程度的几何一致性比以前的单目重建方法。从视觉上看,我们的结果似乎更稳定。我们的算法是能够处理具有挑战性的手持捕获的输入视频与适度的动态运动。重建质量的提高使几个应用程序,如场景重建和先进的基于视频的视觉效果。

英文摘要:

We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Unlike the ad-hoc priors in classical reconstruction, we use a learning-based prior, i.e., a convolutional neural network trained for single-image depth estimation. At test time, we fine-tune this network to satisfy the geometric constraints of a particular input video, while retaining its ability to synthesize plausible depth details in parts of the video that are less constrained. We show through quantitative validation that our method achieves higher accuracy and a higher degree of geometric consistency than previous monocular reconstruction methods. Visually, our results appear more stable. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion. The improved quality of the reconstruction enables several applications, such as scene reconstruction and advanced video-based visual effects.

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。

↑