کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
443030 692465 2016 8 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Upright orientation of 3D shapes with Convolutional Networks
ترجمه فارسی عنوان
گرایش عمودی اشکال 3D با شبکه های کانولوشن
کلمات کلیدی
گرایش عمودی؛ تجزیه و تحلیل شکل داده محور؛ شبکه های کانولوشن
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر گرافیک کامپیوتری و طراحی به کمک کامپیوتر
چکیده انگلیسی


• We present a data-driven method for 3D object upright orientation estimation using 3D Convolutional Networks.
• General objects, including asymmetric ones, can be handled by this approach thanks to the learning ability of ConvNets.
• The proposed method is at least 30 times faster than existing methods.

Posing objects in their upright orientations is the very first step of 3D shape analysis. However, 3D models in existing repositories may be far from their right orientations due to various reasons. In this paper, we present a data-driven method for 3D object upright orientation estimation using 3D Convolutional Networks (ConvNets), and the method is designed in the style of divide-and-conquer due to the interference effect. Thanks to the public big 3D datasets and the feature learning ability of ConvNets, our method can handle not only man-made objects but also natural ones. Besides, without any regularity assumptions, our method can deal with asymmetric and several other failure cases of existing approaches. Furthermore, a distance based clustering technique is proposed to reduce the memory cost and a test-time augmentation procedure is used to improve the accuracy. Its efficiency and effectiveness are demonstrated in the experimental results.

Figure optionsDownload as PowerPoint slide

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Graphical Models - Volume 85, May 2016, Pages 22–29
نویسندگان
, , ,