5 datasets found

Generating videos with content and motion variations is a challenging task in computer vision. The proposed model is trained in an end-to-end manner, without the need to utilize...

The dataset used in the paper is not explicitly described, but it is mentioned that the authors collect 3K videos (60-90 seconds long) from the internet to train their model.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a pre-trained Stable Diffusion model and a Latent Optical Flow Network...

The dataset used in the paper for video-to-4D generation and motion transfer.

The dataset used in the paper for video-to-4D generation and motion transfer.