arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.04072cs.CV
收藏

PlaneRCNN:从单幅图像进行三维平面检测和重建

PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image

NVIDIA(英伟达);Washington University in St. Louis(圣路易斯华盛顿大学);SenseTime(商汤科技);Simon Fraser University(西蒙弗雷泽大学)

Chen Liu, Kihwan Kim, Jinwei Gu, Yasutaka Furukawa, Jan Kautz

摘要:

本文提出了一种深度神经架构PlaneRCNN,它可以从单个RGB图像中检测和重建分段平面表面。PlaneRCNN使用Mask R-CNN的变体来检测具有平面参数和分割掩码的平面。然后,PlaneRCNN联合细化所有的分割掩码,并在训练过程中使用新的损失来执行与附近视图的一致性。该论文还提出了一个新的基准,在地面实况中具有更细粒度的平面分割,其中PlaneRCNN优于现有的最先进的方法,在平面检测,分割和重建指标中具有显著的余量。PlaneRCNN朝着强大的平面提取迈出了重要的一步,这将对包括机器人技术,增强现实和虚拟现实在内的广泛应用产生直接影响。

英文摘要:

This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image. PlaneRCNN employs a variant of Mask R-CNN to detect planes with their plane parameters and segmentation masks. PlaneRCNN then jointly refines all the segmentation masks with a novel loss enforcing the consistency with a nearby view during training. The paper also presents a new benchmark with more fine-grained plane segmentations in the ground-truth, in which, PlaneRCNN outperforms existing state-of-the-art methods with significant margins in the plane detection, segmentation, and reconstruction metrics. PlaneRCNN makes an important step towards robust plane extraction, which would have an immediate impact on a wide range of applications including Robotics, Augmented Reality, and Virtual Reality.

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。

↑