Reproduce “Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussians” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hongru Yan, Xiang Zhang, Zeyuan Chen, Fangyin Wei, Zhuowen Tu
Gaussian Swaying models each Gaussian as a surface patch with area and normal, using them for aerodynamic forces and shading. In a synthetic flag benchmark, it is compared with PhysGaussian using reference videos. On Pattern 3, it reports PSNR 18.60, CD 0.0066, and FVD 219.94, outperforming PhysGaussian on all three metrics. This result applies to the synthetic benchmark, not real-world aerodynamic ground truth.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.