Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGC

2025-02-10

AI Summary

Current AIGC approaches for 3D/4D generation suffer from pervasive physical distortions—unrealistic deformations, unstable motion, and implausible interactions—stemming from an overreliance on appearance consistency while neglecting physical priors. This paper presents the first systematic survey of physics-driven AIGC methods, proposing a unified classification framework spanning multiple representations (e.g., NeRF, 3D Gaussian Splatting, multi-view geometry) and dimensions (3D/4D). We integrate rigid- and soft-body dynamics simulation, differentiable rendering, and physics-constrained modeling to delineate method applicability across material properties and dynamical regimes. Our analysis identifies shared limitations in structural stability, deformation plausibility, and interaction fidelity across existing works, and prescribes concrete optimization pathways. The study establishes theoretical foundations and practical guidelines for developing physically consistent, predictable, and editable generative models.

Technology Category

Computer Vision: Low Level & Physics-based VisionSearch and Optimization: Sampling/Simulation-based SearchHumans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systemsEconomics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applicationsSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Recent advancements in AI-generated content have significantly improved the realism of 3D and 4D generation. However, most existing methods prioritize appearance consistency while neglecting underlying physical principles, leading to artifacts such as unrealistic deformations, unstable dynamics, and implausible objects interactions. Incorporating physics priors into generative models has become a crucial research direction to enhance structural integrity and motion realism. This survey provides a review of physics-aware generative methods, systematically analyzing how physical constraints are integrated into 3D and 4D generation. First, we examine recent works in incorporating physical priors into static and dynamic 3D generation, categorizing methods based on representation types, including vision-based, NeRF-based, and Gaussian Splatting-based approaches. Second, we explore emerging techniques in 4D generation, focusing on methods that model temporal dynamics with physical simulations. Finally, we conduct a comparative analysis of major methods, highlighting their strengths, limitations, and suitability for different materials and motion dynamics. By presenting an in-depth analysis of physics-grounded AIGC, this survey aims to bridge the gap between generative models and physical realism, providing insights that inspire future research in physically consistent content generation.

Problem

• Enhancing structural integrity in AIGC
• Improving motion realism with physics priors
• Bridging gap between generative models and physical principles

Innovation

• Integrates physics priors
• Enhances 3D and 4D realism
• Uses physical simulations