PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives

Zachary Lee, Maxwell Jacobson, Yexiang Xue

arXiv:2605.11266 · 2026-05-13 공개 · arXiv · PDF

visual-quality physics-simulation shape-optimization aerodynamic-lift physical-functionality differentiable-physics physics-guided

Abstract

Recent advances in Gaussian Splatting have enabled fast, high-fidelity 3D scene generation, yet these methods remain purely visual and lack an understanding of how shapes behave in the physical world. We introduce Physics-Guided 3D Gaussian Splatting (PG-3DGS), a framework that couples differentiable physics simulation with 3D Gaussian representations to generate 3D structures satisfying physics functionalities. By allowing physical objectives to guide the shape optimization process alongside visual losses, our approach produces geometries that are not only photometrically accurate but also physically functional. The model learns to adjust shapes so that the generated objects exhibit physically meaningful behaviors, for example, teapots that can pour and airplanes that can generate lift, without sacrificing visual quality. Experiments on pouring and aerodynamic lift tasks show that PG-3DGS improves physical functionality while preserving visual quality. In addition to simulation gains, bench-top physical lift tests with 3D-printed aircraft (Cessna, B-2 Spirit, and paper plane) under identical airflow conditions show higher scale-measured lift for PG-3DGS, generated structures than an appearance-matching baseline in all three cases. Our unified framework connects appearance-based reconstruction with physics-based reasoning, enabling end-to-end generation of 3D structures that both look realistic and function correctly.

한국어 요약

📋 한 줄 요약

**[3D 생성 / 물리 기반 AI]** 미분 가능 물리 시뮬레이션과 3D Gaussian Splatting을 결합하여 시각적으로 정확할 뿐 아니라 물리적으로도 기능하는 3D 구조를 생성하는 PG-3DGS 프레임워크 제안.

🎯 핵심 기여도

💡 핵심 아이디어

3D 표현이 단지 "어떻게 보이는가"뿐만 아니라 "어떻게 거동하는가"까지 학습해야 한다는 통찰. 미분 가능 물리 시뮬레이션의 그래디언트를 시각 손실과 함께 Gaussian 파라미터로 전파하면, 형상이 자연스럽게 물리 기능을 만족하도록 미세 조정된다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 생성된 3D 자산이 시뮬레이션과 실제 세계 양쪽에서 "동작"해야 하는 로보틱스·제품 디자인·과학 시각화 영역의 새로운 표준을 제시. **한계**: 다룬 물리 태스크가 pouring·lift로 제한적이며, 다물리(multi-physics)나 동적 마찰·접촉 등 복잡 시나리오로의 확장은 추가 검증 필요.

🚀 실용적 활용