We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape.
In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.
Ranked #2 on
3D Object Classification
on ModelNet40
3D FEATURE MATCHING 3D GEOMETRY PERCEPTION 3D OBJECT CLASSIFICATION 3D OBJECT RECONSTRUCTION 3D PART SEGMENTATION 3D POINT CLOUD MATCHING 3D SHAPE GENERATION 3D SHAPE REPRESENTATION
We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families; and (iii) can be used to generate a great diversity of realistic structured shape geometries.
To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses.
3D HUMAN POSE ESTIMATION 3D HUMAN RECONSTRUCTION 3D SHAPE GENERATION 3D SHAPE MODELING
Given such a source 3D model and a target which can be a 2D image, 3D model, or a point cloud acquired as a depth scan, we introduce 3DN, an end-to-end network that deforms the source model to resemble the target.
The new tensor data representation is used as input to Generative Adversarial Networks for the task of 3D shape generation.
3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface.
3D generative shape modeling is a fundamental research area in computer vision and interactive computer graphics, with many real-world applications.
We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion.
Ranked #4 on
3D Object Recognition
on ModelNet40
3D OBJECT CLASSIFICATION 3D OBJECT RECOGNITION 3D RECONSTRUCTION 3D SHAPE GENERATION
To alleviate this consequence induced by a huge number of feasible combinations, we propose a combinatorial 3D shape generation framework.