-
Synthesized Images using Metasurface-Based Architecture
The dataset used in the paper is a collection of images synthesized using the proposed metasurface-based architecture. -
GAN Training Dataset
The dataset used for training the generative adversarial network (GAN) model. -
MSRA-TD500
The MSRA-TD500 dataset is a benchmark for scene text detection, containing 700 training images and 200 test images, with multi-lingual, arbitrary-oriented and long text lines. -
Verisimilar Image Synthesis for Detection and Recognition of Texts
The proposed scene text image synthesis technique starts with two types of inputs including “Background Images” and “Source Texts” as illustrated in column 1 and 2 in Fig. 1. -
DrawTextExt
The dataset is used to train the GlyphDraw model for visual text generation. It contains 792k images with 3.3M characters in images and more than 4.8k common unique Chinese... -
High-resolution image synthesis with latent diffusion models
High-resolution image synthesis with latent diffusion models. -
Stable Diffusion v2 release
Stable diffusion v2 release -
Dsprites and 3DShapes
The dataset used in the paper is Dsprites and 3DShapes, which are popular disentanglement evaluation datasets. -
LSUN Conference Rooms
LSUN Conference Rooms -
New Dataset for Zero-Shot Performance Comparison of Spatial Conditions
The dataset used in the paper is a new dataset for zero-shot performance comparison of spatial conditions. -
Denoising Diffusion Implicit Models
The dataset used in the paper for training and testing the Denoising Diffusion Implicit Models. -
Amodal Segmentation by Synthesizing Wholes
A synthetic dataset containing occluded objects paired with their whole counterparts. -
T2I-Compbench-Count
A benchmark for open-world compositional text-to-image generation. The dataset consists of 218 prompts with a single object and its number. -
Stargan v2: Diverse image synthesis for multiple domains
Stargan v2 dataset -
LAION-400M dataset
The LAION-400M dataset is a large collection of images and captions that represent different cultures from around the world. -
Cross-Cultural Understanding Benchmark (CCUB)
The CCUB dataset is a collection of images and captions that represent different cultures from around the world.
