Dataset - LDM

2D Shapes

The 2D Shapes dataset used for disentangled representation learning.
- Dataset
- JSON
ControlVAE: Controllable Variational Autoencoder

The dataset used for language modeling, disentangled representation learning, and image generation.
- Dataset
- JSON
Disentangled Representation Learning

Disentangled representation learning endeavours to train a model proficient in disentangling the underlying factors of observed data.
- Dataset
- JSON
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably...
- Dataset
- JSON
MPI3D

MPI3D is a benchmark dataset that consists of 1,036,800 examples of 3D objects from three different domains: Toy, RealisticC, and Real.
- Dataset
- JSON
Dancer99

The dataset Dancer99 consists of solo dance videos of 99 subjects, with different choreography and background music, providing a robust evaluation of the proposed method’s...
- Dataset
- JSON
Dancer101

The dataset Dancer101 consists of solo dance videos of 101 subjects from the public domain, providing a benchmark to prompt the development of HMT methods.
- Dataset
- JSON
An Identity-Preserved Framework for Human Motion Transfer

Human motion transfer (HMT) aims to generate a video clip for the target subject by imitating the source subject’s motion. Although previous methods have achieved good results...
- Dataset
- JSON

You can also access this registry using the API (see API Docs).

8 datasets found