-
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). -
Solar Power Dataset
The dataset consists of real-life solar power production data. -
Spiral Dataset
The dataset used in the paper is a synthetic dataset consisting of points in 2D that follow a spiral distribution. -
Generative time series models using Neural ODE in Variational Autoencoders
The dataset consists of time series data in the form of spring oscillations, solar power production data, and spiral data. -
Diffusion Random Feature Model
Diffusion probabilistic models have been successfully used to generate data from noise. However, most diffusion models are computationally expensive and difficult to interpret... -
Product Design Conception Dataset
The dataset used in this paper for product design conception. -
Generative Model Evaluation
The dataset used in this paper for generative model evaluation, consisting of 4.1M images from 41 state-of-the-art generative models spanning diffusion models, GANs, variational... -
Biometric Capacity of Generative Face Models
This dataset is used to estimate the biometric capacity of generative face models. -
Normalizing Flow Model
The dataset used in the paper is a normalizing flow model, which is a type of generative model. The model is trained to generate data distributions from a given data... -
A Bayesian Non-parametric Approach to Generative Models
Generative models have emerged as a promising technique for producing high-quality im-ages that are indistinguishable from real images. -
3DShape2VecSet
3DShape2VecSet: A 3D shape representation for neural fields and generative diffusion models -
Autoencoder for processing simple geometric attributes
The dataset used in the paper is a collection of grey-level images of centred disks with varying radii. -
NotImageNet32
A high-quality synthetic dataset created for evaluating generative models
