TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation

  title={TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation},
  author={William Gao and April Wang and Gal Metzer and Raymond A. Yeh and Rana Hanocka},
We present TetGAN, a convolutional neural network designed to generate tetrahedral meshes. We represent shapes using an irregular tetrahedral grid which encodes an occupancy and displacement field. Our formulation enables defining tetrahedral convolution, pooling, and upsampling operations to synthesize explicit mesh connectivity with variable topological genus. The proposed neural network layers learn deep features over each tetrahedron and learn to extract patterns within spatial regions across… 

Tetrahedral Diffusion Models for 3D Shape Generation

Tetrahedral diffusion models are introduced, an extension of DDMs to tetrahedral partitions of 3D space that yields plausible, visually pleasing and diverse 3D shapes, is able to handle surface attributes like color, and can be guided at test time to manipulate the resulting shapes.

LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing

This work presents a new, compelling alternative for representing shapes using a sequence of cross-sectional closed loops, and demonstrates that loops are intuitive and natural primitive for analyzing and editing shapes, both computationally and for users.



Occupancy Networks: Learning 3D Reconstruction in Function Space

This paper proposes Occupancy Networks, a new representation for learning-based 3D reconstruction methods that encodes a description of the 3D output at infinite resolution without excessive memory footprint, and validate that the representation can efficiently encode 3D structure and can be inferred from various kinds of input.

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

This work proposes a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions and introduces the "Frechet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score.

Auto-Encoding Variational Bayes

A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.

Adversarial Generation of Continuous Implicit Shape Representations

This work presents a generative adversarial architecture for generating three-dimensional shapes based on signed distance representations, and studies the effects of using either progressively growing voxel- or point-processing networks as discriminators, and proposes a refinement scheme to strengthen the generator's capabilities in modeling the zero iso-surface decision boundary of shapes.

Extracting Triangular 3D Models, Materials, and Lighting From Images

This work outputs triangle meshes with spatially-varying materials and environment lighting that can be deployed in any traditional graphics engine unmodified, and introduces a differentiable formulation of the split sum approximation of environment lighting to efficiently recover all-frequency lighting.

Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis

We introduce DMTET, a deep 3D conditional generative model that can synthesize high-resolution 3D shapes using simple user guides such as coarse voxels. It marries the merits of implicit and explicit

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

The Deformable Tetrahedral Meshes (DefTet) approach is introduced, which is the first to showcase high-quality 3D tetrahedral meshes results using only a single image as input, and can produce high-fidelity reconstructions with a significantly smaller grid size than alternative volumetric approaches.

ShapeNet: An Information-Rich 3D Model Repository

ShapeNet contains 3D models from a multitude of semantic categories and organizes them under the WordNet taxonomy, a collection of datasets providing many semantic annotations for each 3D model such as consistent rigid alignments, parts and bilateral symmetry planes, physical sizes, keywords, as well as other planned annotations.

Active co-analysis of a set of shapes

A semi-supervised learning method where the user actively assists in the co-analysis by iteratively providing inputs that progressively constrain the system, which introduces a novel constrained clustering method which embeds elements to better respect their inter-distances in feature space together with the user-given set of constraints.

The Shape Matching Element Method: Direct Animation of Curved Surface Models

We introduce a new method for direct physics-based animation of volumetric curved models, represented using NURBS surfaces. Our technical contribution is the Shape Matching Element Method (SEM). SEM