Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces

By Haibin Huang, Evangelos Kalogerakis, Benjamin M. Marlin. 2015

65 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images (2015, background): “Several recent works [17, 5, 31, 13] also extract deep learning features for retrieval and classification of CAD models.”
SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (2017, background): “Recent approaches for assembly-based 3D shape creation from components use probabilistic models [5, 15], or deep-learned models [13].”
Deformation-driven shape correspondence via shape recognition (2017, background): “Unlike Jain et al. [2012], we do not require prior knowledge of part hierarchies.”
3D Object Reconstruction from a Single Depth View with Adversarial Learning (2017, background): “In the past two years, a number of works [13] [60] [15] [21] apply such generative models to learn latent space to represent 3D object shapes, and then to solve simple discriminative tasks such as new image generation, object classification, recognition and shape retrieval.”
PiGraphs (2016, methodology): “The increasing availability of 3D object mesh data led to work in datadriven shape synthesis [Kalogerakis et al. 2012; Huang et al. 2015; Yumer et al. 2015].”
Multi-content GAN for Few-Shot Font Style Transfer (2017, unknown): “Various geometry modeling techniques have been proposed for learning structural priors from example 3D shapes [9, 14] and transferring style from a few examples to an input model [21].”
3D Shape Segmentation with Projective Convolutional Networks (2016, methodology): “Other approaches segment shapes by employing non-rigid alignment steps through deformable part templates [27, 20], or transfer labels through surface correspondences and functional maps between 3D shapes [48, 22, 50, 27, 23].”
Interactive 3D Modeling with a Generative Adversarial Network (2017, background): “More recently, probabilistic models of part hierarchies [Huang et al. 2015; Kalogerakis et al. 2012] and grammars of shape features [Dang et al. 2015] have been learned from collections and used to assist synthesis of new shapes.”