60 datasets found

Videofusion: Decomposed diffusion models for high-quality video generation.

A framework for adding diverse controls to any image/video diffusion model

The dataset used in this paper for training and testing the Videocrafter2 model.

The dataset used in this paper for training and testing the SVD model.

The dataset used in this paper for training and testing the CV-VAE model.

The Kinetics-400 and Kinetics-600 datasets are video understanding datasets used for learning rich and multi-scale spatiotemporal semantics from high-dimensional videos.

The Kinetics-600 dataset consists of 392k training videos and 30k validation videos in 600 human action categories.

The dataset used in the paper is a video dataset, which contains videos with different camera motions.

Generating coherent and natural movement is the key challenge in video generation. This research proposes to condense video generation into a problem of motion generation, to...

Generating coherent and natural movement is the key challenge in video generation. This research proposes to condense video generation into a problem of motion generation, to...

Generating coherent and natural movement is the key challenge in video generation. This research proposes to condense video generation into a problem of motion generation, to...

The DynamiCrafter dataset is a collection of open-domain images used for animating images with video diffusion priors.

The dataset used in the paper is MSR-VTT, a large video description dataset for bridging video and language. The dataset contains 10k video clips with length varying from 10 to...

The dataset used in this paper for text-to-video generation, consisting of short video clips.

A video dataset used for testing the proposed method.

A diffusion-based 2D avatar generation framework to produce realistic and high-quality anchor-style human videos.

The UCF101 dataset contains 13320 videos distributed in 101 action categories. This dataset is different from the above ones in that it contains mostly coarse sports activities...

The authors used the pre-trained diffusion-based text-to-video (T2V) generation model without additional fine-tuning.

UCF101 dataset is used to test the proposed text-to-video model. The dataset contains 101 action categories, and each category has 10 videos. The videos are labeled with text...

A large-scale generated video benchmark dataset for network training and evaluation, comprising synthetic videos from 11 different generator models.