Learning Local Shape Descriptors from Part Correspondences with Multiview Convolutional Networks
ACM Trans. Graph., Volume 37, Issue 1, 2018, Pages 6:1-6:14.
Local 3D shape descriptors convolutional networks shape matching
We present a new local descriptor for 3D shapes, directly applicable to a wide range of shape analysis problems such as point correspondences, semantic segmentation, affordance prediction, and shape-to-scan matching. The descriptor is produced by a convolutional network that is trained to embed geometrically and semantically similar point...More
Full Text (Upload PDF)
PPT (Upload PPT)