… We develop a unified framework based on deep neural network (DNN) for learning 3D deep
shape descriptors with the application in 3D shape retrieval. The proposed method utilizes …

… In this paper, we propose a deep shape descriptor with the discriminative auto-encoder
for shape matching and retrieval, which is insensitive to geometric structure variations. By …

… In this paper, we have proposed a novel deep shape descriptor for 3D shape retrieval.
We first computed the multiscale shape distribution features and then trained a set …

… was to review shape retrieval methods, 3D shape descriptors as a fundamental step in
shape retrieval were also thoroughly discussed. The first survey on 3D shape descriptors was …

… Then we prove that our proposed shape descriptors can be applied to 3D shape recognition
tasks, and verify the improvements made by the multi-scaled feature representation. In …

… a 3D shape descriptor network, which is a deep convolutional energy-based model, for
modeling volumetric shape … The model can synthesize 3D shape patterns by sampling from the …

… 3D geometric data. In this paper, powered with a novel design of adversarial networks (3D-A-Nets),
we have developed a novel 3D deep dense shape descriptor (3D-DDSD) to address …

… Methods using CNN for 3D non-rigid shape analysis such as [1, 19] focus on deriving
robust shape descriptors suitable for local shape correspondence. The potential of CNN’s to …

For 3D shape analysis, an effective and efficient feature is the key to popularize its applications
in 3D domain. In this paper, we present a novel framework to learn and extract local deep …

In this paper, we present a deep learning framework for efficient 3D shape classification
using geodesic moments. Our approach inherits many useful properties from the geodesic …