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 representations 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.

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。