Structurenet: Hierarchical graph networks for 3d shape generation
The ability to generate novel, diverse, and realistic 3D shapes along with associated part
semantics and structure is central to many applications requiring high-quality 3D assets or …
semantics and structure is central to many applications requiring high-quality 3D assets or …
Grass: Generative recursive autoencoders for shape structures
We introduce a novel neural network architecture for encoding and synthesis of 3D shapes,
particularly their structures. Our key insight is that 3D shapes are effectively characterized by …
particularly their structures. Our key insight is that 3D shapes are effectively characterized by …
A comprehensive overview of methodologies and performance evaluation frameworks in 3D mesh segmentation
P Theologou, I Pratikakis, T Theoharis - Computer Vision and Image …, 2015 - Elsevier
Abstract 3D mesh segmentation has become a crucial part of many applications in 3D shape
analysis. In this paper, a comprehensive survey on 3D mesh segmentation methods is …
analysis. In this paper, a comprehensive survey on 3D mesh segmentation methods is …
3D mesh labeling via deep convolutional neural networks
K Guo, D Zou, X Chen - ACM Transactions on Graphics (TOG), 2015 - dl.acm.org
This article presents a novel approach for 3D mesh labeling by using deep Convolutional
Neural Networks (CNNs). Many previous methods on 3D mesh labeling achieve impressive …
Neural Networks (CNNs). Many previous methods on 3D mesh labeling achieve impressive …
Canonical capsules: Self-supervised capsules in canonical pose
We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule
decompositions of objects through permutation-equivariant attention, and self-supervise the …
decompositions of objects through permutation-equivariant attention, and self-supervise the …
Structure-aware shape processing
Shape structure is about the arrangement and relations between shape parts. Structure-
aware shape processing goes beyond local geometry and low level processing to analyze …
aware shape processing goes beyond local geometry and low level processing to analyze …
LaSeSOM: A latent and semantic representation framework for soft object manipulation
Soft object manipulation has recently gained popularity within the robotics community due to
its potential applications in many economically important areas. Although great progress has …
its potential applications in many economically important areas. Although great progress has …
Partnet: A recursive part decomposition network for fine-grained and hierarchical shape segmentation
Deep learning approaches to 3D shape segmentation are typically formulated as a multi-
class labeling problem. These models are trained for a fixed set of labels, which greatly …
class labeling problem. These models are trained for a fixed set of labels, which greatly …
Semantic shape editing using deformation handles
ME Yumer, S Chaudhuri, JK Hodgins… - ACM Transactions on …, 2015 - dl.acm.org
We propose a shape editing method where the user creates geometric deformations using a
set of semantic attributes, thus avoiding the need for detailed geometric manipulations. In …
set of semantic attributes, thus avoiding the need for detailed geometric manipulations. In …
Deep part induction from articulated object pairs
Object functionality is often expressed through part articulation--as when the two rigid parts
of a scissor pivot against each other to perform the cutting function. Such articulations are …
of a scissor pivot against each other to perform the cutting function. Such articulations are …