This is a literature review and code implementation for the video prediction task

Given n seed frames of a video, predict the next m frames.

Open Source Implementation

Lab CudaVision: Video Prediction project

Prediction of future frames and segmenting it.

Dilated convolutional neural network-based deep reference picture generation for video compression (ICASSP 2022)

Experimental fork of TimeSformer from Facebook AI to extend the attention-based model to video generation.

Experimental fork of TimeSformer from Facebook AI to extend the attention-based model to video generation.

Helpers for loading, perprocessing and visualizing the SynpickVP dataset for video-based prediciton tasks

Website for our ICCV 2021 paper "SLAMP: Stochastic Latent Appearance and Motion Prediction". Preprint: https://arxiv.org/abs/2108.02760

Collection of High Performance Deep Learning Models for Video Prediction with experiments

Masterthesis by Fabian Hofmann (2021, @TU-Berlin/DOS)

Flood prediction on aerial-views with deep learning. Based on PARFLOOD from HyLab, University of Parma.

PredVDM: A Video Prediction Model based on Latent Diffusion

Synthetically Generated Surveillance Perspective Human Action Recognition Dataset: 6901 Videos from 10 action classes, made by a 3D Simulation, all cropped spatio-temporally and filmed from a surveillance-camera like position.

Official implementation of "Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks." by Villar-Corrales et al.

Video generation using Stable Diffusion.

Quick Overview of Video Prediction with Deep Learning