Chenguo Lin (@lin_chenguo)

2025-02-03 | โค๏ธ 26 | ๐Ÿ” 2


๐ŸšจICLR๐Ÿšจ

Thank @janusch_patas for featuring our work! Project with @yuchenlin0612 ๐Ÿซก Congratulations ๐Ÿฅณ

Constitutive attributes of 3DGS for various physical phenomena are optimized from a text-to-video model.

2025 is the year of physics-based AI!

Code: https://github.com/wgsxm/OmniPhysGS

๐Ÿ”— ์›๋ณธ ๋งํฌ


Auto-generated - needs manual review

์ธ์šฉ ํŠธ์œ—

MrNeRF (@janusch_patas)

OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation

Abstract (excerpt): We propose OmniPhysGS for synthesizing a physics-based 3D dynamic scene composed of more general objects.

A key design of OmniPhysGS is treating each 3D asset as a collection of constitutive 3D Gaussians. For each Gaussian, its physical material is represented by an ensemble of 12 physical domain-expert sub-models (rubber, metal, honey, water, etc.), greatly enhancing the flexibility of the proposed model.

In the implementation, we define a scene by user-specified prompts and supervise the estimation of material weighting factors via a pretrained video diffusion model. Comprehensive experiments demonstrate that OmniPhysGS achieves more general and realistic physical dynamics across a broader spectrum of materials, including elastic, viscoelastic, plastic, and fluid substances, as well as interactions between different materials.

Our method surpasses existing methods by approximately 3% to 16% in metrics of visual quality and text alignment.

์›๋ณธ ํŠธ์œ—

๐ŸŽฌ ์˜์ƒ

Tags

domain-vision-3d domain-simulation domain-dev-tools domain-visionos