thuml/MotionRNN

About Code release for "MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions" (CVPR 2021) https://arxiv.org/abs/2103.02243

30
/ 100
Emerging

This project helps researchers and engineers working with video data to predict future frames more accurately. It takes a sequence of past video frames as input and generates a prediction of what subsequent frames will look like, even when objects or scenes have complex, varying movements. Scientists, surveillance analysts, or anyone developing systems that anticipate motion would use this to improve video forecasting.

No commits in the last 6 months.

Use this if you need to predict future actions or changes in video sequences where motions are complex and vary across different parts of the scene.

Not ideal if your video prediction needs are simple, involve static scenes, or if you are not comfortable with machine learning model training and evaluation.

video-prediction motion-forecasting computer-vision video-analytics time-series-forecasting
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

57

Forks

8

Language

Python

License

Last pushed

Jul 10, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/thuml/MotionRNN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.