3D ShapeNets: A deep representation for volumetric shapes
Refereed conference paper presented and published in conference proceedings

香港中文大學研究人員
替代計量分析
.

其它資訊
摘要3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect), it is becoming increasingly important to have a powerful 3D shape representation in the loop. Apart from category recognition, recovering full 3D shapes from view-based 2.5D depth maps is also a critical part of visual understanding. To this end, we propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. Our model, 3D ShapeNets, learns the distribution of complex 3D shapes across different object categories and arbitrary poses from raw CAD data, and discovers hierarchical compositional part representation automatically. It naturally supports joint object recognition and shape completion from 2.5D depth maps, and it enables active object recognition through view planning. To train our 3D deep learning model, we construct ModelNet - a large-scale 3D CAD model dataset. Extensive experiments show that our 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.
著者Wu Z., Song S., Khosla A., Yu F., Zhang L., Tang X., Xiao J.
會議名稱IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
會議開始日07.06.2015
會議完結日12.06.2015
會議地點Boston
會議國家/地區美國
詳細描述organized by IEEE,
出版年份2015
月份10
日期14
卷號07-12-June-2015
頁次1912 - 1920
國際標準書號9781467369640
國際標準期刊號1063-6919
語言英式英語

上次更新時間 2020-05-08 於 01:41