Spaghetti splatting enables better 3D curve rendering and simulation
Spaghetti Splatting: Differentiating Curvilinear Dirac Masses via Convolution
Computer Vision and Pattern RecognitionGraphics
Summary
3D shapes in computers are often made up of tiny points, lines, and triangles, but lines are hard to handle because they're infinitely thin. The authors introduce a method called Spaghetti Splatting that treats curved lines as connected short segments smeared out smoothly, making them easier to render and learn from images. Their method produces smooth, connected curves that avoid visual glitches and can be used directly in physics simulations. This approach also works naturally for points and is competitive with other techniques for general 3D scenes.
What this means in practice
- •For 3d graphics engineers: Render smooth and connected 3D curves from volume data with fewer artifacts and native support for anti-aliasing.
- •For game physics developers: Integrate long connected strands directly into physics simulations for realistic hair, cables, or rope effects.
Authors
George Shramko, Shrisudhan Govindarajan, Rudy Lam, Yizheng Xie, Daniel Rebain, David B. Lindell, Andrea Tagliasacchi
Abstract
In production systems, 3D geometry is represented by primitives such as points, lines, and triangles, as rendering hardware is optimized to generate images from them very efficiently. Learning such primitives from images by volume rendering is challenging, as they are Dirac masses defined at infinitesimal locations in space. EWA splatting, Poisson reconstruction, and 3D Gaussian Splatting overcome this by convolving Dirac masses with a low-frequency kernel, a recipe that generalizes along two axes: the kernel and the primitive. As points and triangles have already received significant attention, we investigate this recipe for curvilinear primitives, and introduce Spaghetti Splatting. We approximate curves by polylines whose convolution converges to that of the continuous curve, and volume render each segment so that connected segments composite without overcounting at their joints. For fast training and inference, we linearize the camera projection per segment, which also accommodates kernels beyond Gaussians, such as Beta kernels. As a point is a curve of zero length, our representation is a strict superset of 3D Gaussian Splatting. It remains competitive with the state-of-the-art on general scenes, outperforms methods specialized to line-like geometry, natively supports anti-aliasing, and produces long connected strands that are directly amenable to physics simulation.