-
LSUN Bedrooms
The dataset used in the paper is the LSUN bedrooms dataset, a large-scale image dataset. -
ImageDecomp
A dataset of real indoor scenes for training and testing material-aware diffusion models -
Evermotion
A dataset of synthetic indoor scenes for training and testing material-aware diffusion models -
InteriorVerse
A dataset of synthetic indoor scenes for training and testing material-aware diffusion models -
Autoencoder for processing position
The dataset used in the paper is a collection of one-hot vectors representing the position of a Dirac delta function. -
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. -
De-Fake: Detection and Attribution of Fake Images Generated by Text-to-Image ...
The De-Fake dataset is a detection and attribution of fake images generated by text-to-image diffusion models. -
DEFAKE: A Large-Scale Dataset for Real-World Face Forgery Detection
The DEFAKE dataset is a large-scale dataset for real-world face forgery detection, containing 6,000 images generated by Stable Diffusion. -
DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forge...
The DiffusionFace dataset is a comprehensive dataset for diffusion-based face forgery analysis, covering various forgery categories, including unconditional and text-guided... -
Unpaired Image-to-Image Translation
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks -
Apple-to-Orange, Horse-to-Zebra, and Yosemite Summer-to-Winter datasets
The dataset used for unpaired image-to-image translation tasks -
COCO-stuff dataset
The COCO-stuff dataset is a large-scale dataset for scene understanding, object detection, and image synthesis. -
ShiftDDPMs: Exploring Conditional Diffusion Models
Diffusion models have recently exhibited remarkable abilities to synthesize striking image samples since the introduction of denoising diffusion probabilistic models (DDPMs). -
QMUL-Shoe-V2
Fine-grained sketch-based image retrieval (FG-SBIR) aims to minimize the distance between sketches and corresponding images in the embedding space. -
Shoe-leg dataset
A shoe-leg dataset to support the training of the shoe-wearing image generation module. It consists of tuples of raw images, shoe-only images and pose skeleton annotations. -
Shoe-wearing dataset
A shoe-wearing dataset to support the training of each modules above. It consists of a wearable-area detection sub-dataset and a shoe-leg synthesis sub-dataset. -
Diffusion Noise Feature
Diffusion noise feature: Accurate and fast generated image detection. -
LSUN-Bedroom
LSUN-Bedroom dataset is a large-scale dataset of images of bedrooms.