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 1406.2283cs.CV
收藏

使用多尺度深度网络从单个图像预测深度图

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

New York University(纽约大学);Facebook AI Research(Facebook人工智能研究院)

David Eigen, Christian Puhrsch, Rob Fergus

摘要:

预测深度是理解场景的3D几何形状的重要组成部分。虽然对于立体图像,局部对应足以进行估计,但从单个图像中找到深度关系不那么简单,需要整合来自各种线索的全局和局部信息。此外,这项任务本身是模糊的,很大的不确定性来源于总体规模。在本文中,我们提出了一种新方法,通过使用两个深度网络堆栈来解决这一任务:一个是基于整个图像进行粗略的全局预测,另一个是在本地细化此预测。我们还应用尺度不变误差来帮助测量深度关系而不是尺度。通过利用原始数据集作为训练数据的大来源,我们的方法在NYU Depth和KITTI上都实现了最先进的结果,并且在不需要超像素的情况下匹配详细的深度边界。

英文摘要:

Predicting depth is an essential component in understanding the 3D geometry of a scene. While for stereo images local correspondence suffices for estimation, finding depth relations from a single image is less straightforward, requiring integration of both global and local information from various cues. Moreover, the task is inherently ambiguous, with a large source of uncertainty coming from the overall scale. In this paper, we present a new method that addresses this task by employing two deep network stacks: one that makes a coarse global prediction based on the entire image, and another that refines this prediction locally. We also apply a scale-invariant error to help measure depth relations rather than scale. By leveraging the raw datasets as large sources of training data, our method achieves state-of-the-art results on both NYU Depth and KITTI, and matches detailed depth boundaries without the need for superpixelation.

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。

↑