3DShapeNets_supp.pdf: (updated on May 28, 2015) this file contains results on the ModelNet40 dataset.Proceedings of 28th IEEE Conference on Computer Vision and Pattern Recognition ( CVPR2015) XiaoģD ShapeNets: A Deep Representation for Volumetric Shape Modeling We construct a large-scale 3D computer graphics dataset to train our model, and conduct extensive experiments to study this new representation. Our model naturally supports object recognition from 2.5D depth map, and view planning for object recognition. 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. Furthermore, when the recognition has low confidence, it is important to have a fail-safe mode for object recognition systems to intelligently choose the best view to obtain extra observation from another viewpoint, in order to reduce the uncertainty as much as possible. Microsoft Kinect), it is even more urgent to have a useful 3D shape model in an object recognition pipeline.
With the recent boost of inexpensive 2.5D depth sensors (e.g. 3D ShapeNets: A Deep Representation for Volumetric Shapes 3D ShapeNets: A Deep Representation for Volumetric Shapes AbstractģD shape is a crucial but heavily underutilized cue in object recognition, mostly due to the lack of a good generic shape representation.
0 kommentar(er)
