arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.02808cs.CVcs.GR
收藏

基于投影卷积网络的三维形状分割

3D Shape Segmentation with Projective Convolutional Networks

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);University of Cyprus(塞浦路斯大学);IIT Bombay(印度理工学院孟买分校)

Evangelos Kalogerakis, Melinos Averkiou, Subhransu Maji, Siddhartha Chaudhuri

摘要:

本文介绍了一种用于将3D对象分割成其标记的语义部分的深层架构。我们的架构结合了基于图像的全卷积网络(FCN)和基于表面的条件随机场(CRF),以产生3D形状的相干分割。基于图像的FCN用于关于3D对象部件的高效的基于视图的推理。通过一个特殊的投影层,FCN输出有效地聚合在多个视图和比例,然后投影到3D物体表面。最后,一个基于表面的CRF相结合的投影输出与几何一致性线索,产生连贯的分割。整个架构(多视图FCN和CRF)都是端到端训练的。我们的方法在目前最大的分割基准(ShapeNet)中显着优于现有的最先进的方法。最后,我们展示了有前途的分割结果从消费级深度相机获得的嘈杂的3D形状。

英文摘要:

This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield coherent segmentations of 3D shapes. The image-based FCNs are used for efficient view-based reasoning about 3D object parts. Through a special projection layer, FCN outputs are effectively aggregated across multiple views and scales, then are projected onto the 3D object surfaces. Finally, a surface-based CRF combines the projected outputs with geometric consistency cues to yield coherent segmentations. The whole architecture (multi-view FCNs and CRF) is trained end-to-end. Our approach significantly outperforms the existing state-of-the-art methods in the currently largest segmentation benchmark (ShapeNet). Finally, we demonstrate promising segmentation results on noisy 3D shapes acquired from consumer-grade depth cameras.

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。

↑