Learning Descriptor Networks for 3D Shape Synthesis and Analysis
نویسندگان
چکیده
This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the model follows an “analysis by synthesis” scheme and can be interpreted as a mode seeking and mode shifting process. The model can synthesize 3D shape patterns by sampling from the probability distribution via MCMC such as Langevin dynamics. The model can be used to train a 3D generator network via MCMC teaching. The conditional version of the 3D shape descriptor net can be used for 3D object recovery and 3D object super-resolution. Experiments demonstrate that the proposed model can generate realistic 3D shape patterns and can be useful for 3D shape analysis.
منابع مشابه
3D Models Recognition in Fourier Domain Using Compression of the Spherical Mesh up to the Models Surface
Representing 3D models in diverse fields have automatically paved the way of storing, indexing, classifying, and retrieving 3D objects. Classification and retrieval of 3D models demand that the 3D models represent in a way to capture the local and global shape specifications of the object. This requires establishing a 3D descriptor or signature that summarizes the pivotal shape properties of th...
متن کاملCompact Vectors of Locally Aggregated Tensors for 3D Shape Retrieval
During the last decade, a significant attention has been paid, by the computer vision and the computer graphics communities, to three dimensional (3D) object retrieval. Shape retrieval methods can be divided into three main steps: the shape descriptors extraction, the shape signatures and their associated similarity measures, and the machine learning relevance functions. While the first and the...
متن کاملLearning local shape descriptors with view-based convolutional networks
Figure 1: We present a view-based convolutional network that produces local, point-based shape descriptors. The network is trained such that geometrically and semantically similar points across different 3D shapes are embedded close to each other in descriptor space (left). Our produced descriptors are quite generic — they can be used in a variety of shape analysis applications, including dense...
متن کامل3D shape retrieval based on Multi-scale Integral Orientations
In this paper we describe a novel 3D shape retrieval method based on Multi-scale Integral Orientations. In our approach, a 3D model after normalization is represented by a set of depth images captured uniformly on a unit circle. Then the shape descriptor based on the multiscale version of the localized gradient histogram is calculated for each depth image. Finally, the comparison is performed u...
متن کامل3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
Recently researchers have been shifting their focus towards learned 3D shape descriptors from hand-craft ones to better address challenging issues of the deformation and structural variation inherently present in 3D objects. 3D geometric data are often transformed to 3D Voxel grids with regular format in order to be better fed to a deep neural net architecture. However, the computational intrac...
متن کامل