36 datasets found

EscherNet is a multi-view conditioned diffusion model designed for scalable view synthesis. It leverages Stable Diffusion's 2D architecture empowered by the innovative Camera...

The dataset used in this paper is a text-to-image diffusion model, specifically Stable Diffusion v1-5.

This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video translation with user prompts.

Human motion prediction is a classical problem in computer vision and computer graphics, which has a wide range of practical applications. Previous effects achieve great...

The dataset used for training and testing the SE(3) diffusion model.

VegeDiff is a geospatial vegetation forecasting model that uses a diffusion model to capture the uncertainties in vegetation change processes and a variational autoencoder to...

Low-light image enhancement has gained increasing importance with the rapid development of visual creation and editing. However, most existing enhancement algorithms are...

A ground-based dataset and a diffusion model for on-orbit low-light image enhancement

Synthesizing novel 3D models that resemble the input example has long been pursued by graphics artists and machine learning researchers. In this paper, we present Sin3DM, a...

The dataset used in this paper is a large-scale text-to-image diffusion model, which consists of 35 subjects with unique pets and objects.

The dataset used in this paper is a large-scale text-to-image diffusion model, which consists of 35 subjects with unique pets and objects.

The proposed SMDNet model is used for change detection in high-resolution remote sensing images.

Conditional score-based diffusion model for unpaired or partially paired training dataset

Coarse-grained protein models play a crucial role in the study of protein structures, protein thermodynamic properties, and protein conformation dynamics.

GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents

The image-only stickers dataset used for testing the kNN-Diffusion model.

The dataset used for training the kNN-Diffusion model, which consists of a large-scale retrieval method for training a text-to-image model without any text data.

The Fashion dataset is used for human image animation task. It contains videos of humans performing different actions.

MD30 (Manually-annotated Dataset) comprises 30 images chosen from the 807 images. For those images, we discard sn by BLIP2 and attach a more accurate text as sn by a human...

NoiseCollage generates an image with N objects from the following conditions, L, S, and s∗: L = {l1,..., lN } is the N layout conditions to control the layout of individual...