Paired 3D Model Generation with Conditional Generative Adversarial Networks

  title={Paired 3D Model Generation with Conditional Generative Adversarial Networks},
  author={Cihan Ongun and Alptekin Temi̇zel},
Generative Adversarial Networks (GANs) are shown to be successful at generating new and realistic samples including 3D object models. Conditional GAN, a variant of GANs, allows generating samples in given conditions. However, objects generated for each condition are different and it does not allow generation of the same object in different conditions. In this paper, we first adapt conditional GAN, which is originally designed for 2D image generation, to the problem of generating 3D models in… 

3D Topology Transformation with Generative Adversarial Networks

A novel 3D-to-3D topology transformation method using Generative Adversarial Networks (GAN) to transform the volumetric style of a 3D object while retaining the original object shape is shown.

A Survey on Generative Adversarial Networks: Variants, Applications, and Training

This work surveys several training solutions proposed by different researchers to stabilize GAN training, and surveys the original GAN model and its modified classical versions, and detail analysis of various GAN applications in different domains.

SinGAN-3D: towards unconditioned 3D shapes generation

SinGAN-3D, a variation of the deep neural network architecture presented originally by SinGAN, is presented, starting from a single three-dimensional voxelized model, which uses a pyramid of 3D convolutional networks to model the third dimension and exploits periodic activation functions to capture the latent structure of the input model.

Learning geometry-image representation for 3D point cloud generation

A novel geometry image based generator (GIG) is proposed to convert the 3D point cloud generation problem to a 2D geometry image generation problem, which allows the method to create plausible and novel 3D objects, but also learn a probabilistic latent space that well supports the shape editing like interpolation and arithmetic.

Automated Processing and Phenotype Extraction of Ovine Medical Images Using a Combined Generative Adversarial Network and Computer Vision Pipeline

This study applied deep neural networks, in the form of a generative adversarial network (GAN), to perform image-to-image processing steps needed for ovine phenotype analysis from CT scans of sheep using a computer vision (CV) pipeline.

Artificial Neural Networks and Deep Learning in the Visual Arts: a review

An exhaustive analysis of the use of Artificial Neural Networks and Deep Learning in the Visual Arts, which highlights the contributions of photography and pictorial art and other uses for 3D modeling, including video games, architecture, and comics.

GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservation

The proposed automated face recognition system has a higher attack success rate than the state-of-the-art methods and it has the highest quality and are more pleasing to human eyes.

Deep Learning for Automated Product Design

Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography

This survey summarises recent developments in deep learning techniques for data hiding for the purposes of watermarking and steganography, categorising them based on model architectures and noise injection methods.



Improved Adversarial Systems for 3D Object Generation and Reconstruction

This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects by employing the Wasserstein distance normalized with gradient penalization as a training objective.

AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks

This work presents an approach for improving the capability of the methods which are based on conditional GAN, and proposes another model which conditions on multiple information such as domain information and label information which is able to conduct label propagation from the source domain to the target domain.

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

A novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional networks and generative adversarial nets, and a powerful 3D shape descriptor which has wide applications in 3D object recognition.

Representation Learning and Adversarial Generation of 3D Point Clouds

This paper introduces a deep autoencoder network for point clouds, which outperforms the state of the art in 3D recognition tasks, and designs GAN architectures to generate novel point-clouds.

Syncgan: Synchronize the Latent Spaces of Cross-Modal Generative Adversarial Networks

A novel network component named synchronizer is proposed in this work to judge whether the paired data is synchronous/corresponding or not, which can constrain the latent space of generators in the GANs.

Mode Regularized Generative Adversarial Networks

This work introduces several ways of regularizing the objective, which can dramatically stabilize the training of GAN models and shows that these regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training and thus providing a unified solution to the missing modes problem.

Image-to-Image Translation with Conditional Adversarial Networks

Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.

Coupled Generative Adversarial Networks

This work proposes coupled generative adversarial network (CoGAN), which can learn a joint distribution without any tuple of corresponding images, and applies it to several joint distribution learning tasks, and demonstrates its applications to domain adaptation and image transformation.

Conditional Generative Adversarial Nets

The conditional version of generative adversarial nets is introduced, which can be constructed by simply feeding the data, y, to the generator and discriminator, and it is shown that this model can generate MNIST digits conditioned on class labels.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a