awesome-physics-cognition-based-video-generation
github.com/minnie-lin/awesome-physics-cognition-based-video-generation ↗A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.
312
GitHub Stars
248
Curated Resources
7
Categories
2 hours ago
Last Refreshed
WorkshopsSurveysBasic Schematic Perception for GenerationPassive Cognition of Physical Knowledge for GenerationActive Cognition for World SimulationDatasets, Benchmarks and MetricsPhysical Understanding
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me workshops resources from awesome-physics-cognition-based-video-generation"
Installation instructions →What's inside
Workshops
Passive Cognition of Physical Knowledge for Generation
- 3DPhysVideo: 3D Scene Reconstruction and Physical Animation Leveraging a Video Generation Model via Consistency-Guided Flow SDE
-
- AccidentSim: Generating Physically Realistic Vehicle Collision Videos from Real-World Accident Reports
- Articulated Kinematics Distillation from Video Diffusion Models
- Automated 3D Physical Simulation of Open-world Scene with Gaussian Splatting
- AutoVFX: Physically Realistic Video Editing from Natural Language Instructions
- Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
Basic Schematic Perception for Generation
- 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
- Adding Conditional Control to Text-to-Image Diffusion Models
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
- AnimateAnything: Consistent and Controllable Animation for Video Generation
- Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation
- CoCo4D: Comprehensive and Complex 4D Scene Generation
Active Cognition for World Simulation
- AdaWorld: Learning Adaptable World Models with Latent Actions
- Aether: Geometric-Aware Unified World Modeling
- Can vision language models learn intuitive physics from interaction?
- Cosmos world foundation model platform for physical ai
- DeepVerse: 4D Autoregressive Video Generation as a World Model
- Dream to manipulate: Compositional world models empowering robot imitation learning with imagination
Surveys
- Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
- A Survey of Interactive Generative Video
- Digital Gene: Learning about the Physical World through Analytic Concepts
- From Specialist to Generalist: A Comprehensive Survey on World Models
-
- Generative Physical AI in Vision: A Survey
- Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGC
Datasets, Benchmarks and Metrics
- A physical coherence benchmark for evaluating video generation models via optical flow-guided frame prediction
- A Unified Evaluation Benchmark for World Generation
- Beyond Rigid: Benchmarking Non-Rigid Video Editing
- Can Your Model Separate Yolks with a Water Bottle? Benchmarking Physical Commonsense Understanding in Video Generation Model
- ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
- Cognitive Science-Inspired Evaluation of Core Capabilities for Object Understanding in AI
Physical Understanding
- A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
- Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
-
- Bridging the Reality Gap: A Benchmark for Physical Reasoning in General World Models with Various Physical Phenomena beyond Mechanics
-
- Can vision language models learn intuitive physics from interaction?
-
- CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models
- Does Physics Knowledge Emerge in Frontier Models?
Showing a sample of 248 resources. View the full list on GitHub →