Awesome-Physics-Cognition-based-Video-Generation  by minnie-lin

Physics-informed AI for advanced video generation

Created 11 months ago
264 stars

Top 96.7% on SourcePulse

GitHubView on GitHub
Project Summary

This repository serves as a comprehensive, actively maintained catalog of research papers, code, and related resources focused on integrating physical cognition into video generation. It targets researchers and practitioners seeking to understand and advance the state-of-the-art in physically plausible video synthesis, covering text-to-video (T2V), video-to-video (V2V), and dynamic 3D/4D generation, as well as world models and simulators. The project aims to consolidate and organize this rapidly evolving field, offering a valuable reference for the community.

How It Works

The project functions as a structured, curated collection of academic and technical materials. It categorizes research based on its approach to physical cognition, including basic perception, passive knowledge assimilation, and active world simulation. The listed resources span various generation paradigms and related AI concepts, providing a holistic view of research integrating physics into video generation.

Quick Start & Requirements

This repository is a curated list of research resources, not a software project requiring installation. Users can access links to papers, code repositories, and websites for individual research projects. The primary "requirement" is an interest in the field of physics-cognition-based video generation.

Highlighted Details

  • Features a comprehensive survey paper, "Exploring the Evolution of Physics Cognition in Video Generation: A Survey," offering in-depth analysis.
  • Organizes research across key areas: basic perception, passive/active cognition for generation/simulation, and datasets/benchmarks.
  • Covers T2V, V2V, and dynamic 3D/4D generation, including world models and simulators.
  • Actively maintained with ongoing updates to incorporate emerging research.

Maintenance & Community

The repository is actively maintained and updated with new research. It welcomes community contributions, feedback, and suggestions for improving its taxonomy and content. Users are encouraged to submit pull requests for new work or updates.

Licensing & Compatibility

No specific software license is mentioned for the repository itself. The licensing of individual papers, code, or websites linked within the repository would depend on their respective sources.

Limitations & Caveats

As a curated list, its scope is dependent on community contributions and maintainer curation. It points to external resources rather than providing a unified framework or executable code. Users must consult individual links for project-specific details, dependencies, and licenses.

Health Check
Last Commit

2 weeks ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
22 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.