3D Shape Generation

42 papers with code • 0 benchmarks • 1 datasets

Image: Mo et al

Most implemented papers

Learning elementary structures for 3D shape generation and matching

TheoDEPRELLE/AtlasNetV2 NeurIPS 2019

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.

Combinatorial 3D Shape Generation via Sequential Assembly

POSTECH-CVLab/Combinatorial-3D-Shape-Generation 16 Apr 2020

To alleviate this consequence induced by a huge number of feasible combinations, we propose a combinatorial 3D shape generation framework.

Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis

angeladai/cnncomplete CVPR 2017

Although our 3D-EPN outperforms state-of-the-art completion method, the main contribution in our work lies in the combination of a data-driven shape predictor and analytic 3D shape synthesis.

3D Point Capsule Networks

yongheng1991/3D-point-capsule-networks CVPR 2019

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.

StructureNet: Hierarchical Graph Networks for 3D Shape Generation

daerduoCarey/structurenet 1 Aug 2019

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.

ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation

liuzhengzhe/ISS-Image-as-Stepping-Stone-for-Text-Guided-3D-Shape-Generation 9 Sep 2022

Text-guided 3D shape generation remains challenging due to the absence of large paired text-shape data, the substantial semantic gap between these two modalities, and the structural complexity of 3D shapes.

LION: Latent Point Diffusion Models for 3D Shape Generation

nv-tlabs/LION 12 Oct 2022

To advance 3D DDMs and make them useful for digital artists, we require (i) high generation quality, (ii) flexibility for manipulation and applications such as conditional synthesis and shape interpolation, and (iii) the ability to output smooth surfaces or meshes.

DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation

liuzhengzhe/dreamstone-iss 24 Mar 2023

The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between rendered images and the input text.

SurfNet: Generating 3D shape surfaces using deep residual networks

sinhayan/surfnet CVPR 2017

3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface.

Learning a Hierarchical Latent-Variable Model of 3D Shapes

lorenmt/vsl 17 May 2017

We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion.