Popular GitHub Repositories for Video Prediction

Mastering Atari with Discrete World Models

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

Stochastic Adversarial Video Prediction

e3d-lstm; Eidetic 3D LSTM A Model for Video Prediction and Beyond

Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks

Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223

Video Predicting using ConvLSTM and pytorch

A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related websites.

Official implementation of the paper Stochastic Latent Residual Video Prediction

SLAMP: Stochastic Latent Appearance and Motion Prediction

Clockwork VAEs in JAX/Flax

A pytorch reimplement of PredNet, which is a deep recurrent convolutional neural network for video prediction and unsupervised learning.

In this repository, we focus on video frame prediction the task of predicting future frames given a set of past frames. We present an Adversarial Spatio-Temporal Convolutional LSTM architecture to predict the future frames of the Moving MNIST Dataset. We evaluate the model on long-term future frame prediction and its performance of the model on out-of-domain inputs by providing sequences on which the model was not trained.

Learning Robust Dynamics Through Variational Sparse Gating

Official implementation of: "Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions" by Villar-Corrales et al. ICIP 2023

Video generation using Stable Diffusion.

PredVDM: A Video Prediction Model based on Latent Diffusion

A deep learning project to predict and generate future video frames using models like ConvLSTM, PredRNN, and Transformers, leveraging the UCF101 dataset. The repository includes preprocessing, model training, video generation, an interactive UI, and evaluation metrics to compare model performance in video synthesis and temporal prediction tasks.