72 datasets found

FashionSD-X: Multimodal Fashion Garment Synthesis using Latent Diffusion

The dataset used in the paper is not explicitly described, but it is mentioned that the authors compared their results with PLMS.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors compared their results with DPM++.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a 20-step DDIM sampler and a 13-step DDIM sampler.

A large dataset of text-image pairs collected online.

PEOPLE2K contain about 4846 images.

SCAPES2K contains about 13000 images with the theme of natural scenes and all images have pixel above 2048*2048 pixels.

The dataset used in the paper is a large-scale paired dataset for training a NeRF-agnostic restorer. It consists of 8 virtual scenes, each with 400 images.

The dataset used in the paper is a large-scale paired dataset for training a NeRF-agnostic restorer. It consists of 8 different forward-facing scenes with 20-62 high-quality...

The dataset used in the paper is not explicitly mentioned, but it is mentioned that the authors used the AFHQ-Dog dataset for dog generation.

The proposed method, dubbed Dynamic Hyperpixel Flow, learns to compose hypercolumn features on the fly by selecting a small number of relevant layers from a deep convolutional...

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

Diffusion MRI (dMRI) is an essential neuroimaging technique with high acquisition costs. Deep learning approaches have been used to enhance dMRI and predict diffusion biomarkers...

Diffusion models have recently emerged as the state-of-the-art of generative modeling, demonstrating remarkable results in image synthesis and across other modalities.

SDXL: Improving latent diffusion models for high-resolution image synthesis.

The dataset used in this paper for testing the effectiveness of the disguise generation algorithm.

The dataset contains five tabletop real scenes imaged by 352 cameras in a dome.

The dataset contains 80 real-world scenes with image sequences and structured light 3D scans as reference data.

A style-based generator architecture for generative adversarial networks.

The dataset used in the paper is COCO-stuff and Visual Genome. COCO-stuff is a dataset of 164K images with pixel-level stuff annotations, and Visual Genome is a dataset of...