⌁ Awesome World Model Hub Papers · Datasets · Projects
中文 GitHub
← Back to papers

From 2D to 3D Cognition: A Brief Survey of General World Models

arXiv 25.06 2025 59.6 survey

TLDR

A survey categorizing world models transitioning from 2D to 3D cognition, highlighting key technologies and applications in embodied AI, autonomous driving, and gaming.

Reasoning

Strengths: Provides a structured conceptual framework and covers real-world applications. Weaknesses: As a survey, it lacks novel experiments or empirical evaluations; limited to categorization.

Read-first score

Read-first score 59.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 46.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=analysis,metric

Topical relevance 42%
65.7

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 25%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 267.

Keyword Scores

world model
10
generative world model
9
interactive world model
8
world dynamics prediction
8
world simulator
5
model-based reinforcement learning world model
4
video world model
2

Deep Analysis

Innovations

  • Introduces a conceptual framework for categorizing world models transitioning from 2D perception to 3D cognition
  • Highlights two key technological drivers: advances in 3D representations and incorporation of world knowledge
  • Dissects three core cognitive capabilities: 3D physical scene generation, 3D spatial reasoning, and 3D spatial interaction

Methodology

This survey provides a structured and forward-looking review of world models, introducing a conceptual framework to categorize emerging techniques. It highlights two key technological drivers and dissects three core cognitive capabilities, then examines their deployment in real-world applications and identifies challenges across data, modeling, and deployment.

Key Results

The survey systematically categorizes recent 3D-aware generative world models and clarifies their roles in advancing 3D cognitive world models, identifying challenges and future directions for more robust and generalizable 3D world models.

Limitations

  • Challenges across data, modeling, and deployment are identified but not fully resolved
  • The survey is limited to a brief overview and may not cover all emerging techniques in depth

Resources

Paper

Tags