3D shape is a crucial but heavily underutilized cue in object recognition, mostly due to the lack of a good generic shape representation. With the recent boost of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect), it is even more urgent to have a useful 3D shape model in an object recognition pipeline. 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. To this end, we propose to represent a geometric 3D shape as a probabil- ity distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. Our model naturally supports object recognition from 2.5D depth map, and it is the first model that supports view planning for object recognition. We construct a large-scale 3D computer graphics dataset to train our model, and conduct extensive experiments to study this new representation.

使用卷积深度置信网络将几何3D形状表示为3D体素网格上的二元变量的概率分布，以实现物体识别和根据2.5D深度图形完成3D形状恢复等多个方面的任务，利用构建的大规模3D CAD模型数据集 - ModelNet进行训练，可以在各种任务中显著提高性能。

3D ShapeNets：一种用于体积形状的深度表示