Spaghetti Splatting differentiates curvilinear primitives by convolution

arXivarXivPapers

Spaghetti Splatting differentiates curvilinear primitives by convolution
arXiv / Shramko et al.

George Shramko et al. introduce Spaghetti Splatting, a method for learning curvilinear 3D primitives from images by volume rendering. Points, lines and triangles are Dirac masses, so the authors follow the same convolution recipe used by EWA splatting and 3D Gaussian Splatting, approximating curves with polylines whose convolution converges to that of the continuous curve and rendering segments so joints are not overcounted.

Linearizing the camera projection per segment also allows kernels beyond Gaussians, such as beta kernels. Because a point is a curve of zero length, the representation is a strict superset of 3D Gaussian Splatting. The authors say it stays competitive on general scenes, outperforms methods specialized to line-like geometry, supports anti-aliasing, and produces long connected strands that can be used in physics simulation.