-
Hierarchical Exponential-family Energy-based (HEE) model on CIFAR10
The HEE model uses CIFAR10 to demonstrate its ability to generate high-quality images. -
Hierarchical Exponential-family Energy-based (HEE) model
The HEE model uses 2D synthetic datasets and FashionMNIST to validate its capabilities. -
Variational Discriminator Bottleneck
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a 34 degrees-of-freedom humanoid character and a phase-functioned... -
Generative Models for 3D Objects
Generative models for 3D objects -
GAN and VAE from an Optimal Transport Point of View
The dataset used in the paper is a generative model, specifically a Wasserstein GAN and a Wasserstein VAE. -
Synthetic two-dimensional data and MNIST digits
The dataset used in the experiments with the synthetic two-dimensional data and the MNIST digits. -
Density Estimation Using Real NVP
This dataset has no description
-
Alternating Back-Propagation for Generator Networks
This dataset has no description
-
Wasserstein GAN
This dataset has no description
-
Flexible Prior Distributions for Deep Generative Models
The dataset induced prior distribution is learned using a secondary GAN named PGAN. This prior is then used to further train the original GAN. -
Max-Margin Deep Generative Models
Deep generative models (DGMs) are effective on learning multilayered represen- tations of complex data and performing inference of input data by exploring the generative ability. -
Score-based generative model for function spaces
The dataset used in the paper is a score-based generative model for function spaces. -
GenCO: Generating Diverse Designs with Combinatorial Constraints
GenCO: Generating Diverse Designs with Combinatorial Constraints -
DDIM or PLMS
Text-to-image models, such as DDIM or PLMS. -
OpenCLIP and LAION-5B
Language-guided image diffusion models, such as OpenCLIP and LAION-5B. -
Large datasets
Large datasets used to train deep generative models, such as image and audio recordings, manuscripts, and photographs. -
Classifier Score Distillation
Text-to-3D generation has made remarkable progress recently, particularly with methods based on Score Distillation Sampling (SDS) that leverages pre-trained 2D diffusion models. -
Improved Precision and Recall Metric for Assessing Generative Models
The dataset used in the paper is not explicitly described, but it is mentioned that it is a generative model dataset. -
ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation
The dataset used in the paper for text-to-3D synthesis with Asynchronous Score Distillation (ASD).
