RBF Your SDF: Radial Basis Function Interpolation of Signed Distance Fields with Implied Tangent Points

Yong Cheng, Yotam Gingold
ACM SIGGRAPH Asia 2026 (Conference Papers)

Paper

Interactive Explanation (2D Demo)

Supplementary Material

Code

Top row: A wicker chair reconstructed by a variety of algorithms: Marching Cubes, Reach for the Arcs, Maximal Empty Spheres, Ours, Ground Truth. Inset shows a close-up of the chair's armrest. Ground Truth shows sharp edges where the back and leg meet. Ours shows a sharp edge at the same location with some bumps, while the other methods show a rounded edge. The number 75³ is above the Ground Truth. Bottom row: Reconstructions of The Thinker statue by Rodin. There are no inset close-ups. The number 20 ³ is above the Ground Truth. More details are visible in the Ours reconstruction than the others. We marry scattered data interpolation with the tangent sphere observation [Batty 2011; Kobbelt et al. 2001; Sellán et al. 2023] that every Signed Distance Field (SDF) sample implies a point on a sphere tangent to the surface. We propose an iterative procedure to find tangent points consistent with a Radial Basis Function (RBF) interpolating both SDF and tangent point samples. Our algorithm is practical at higher resolutions via a partition-of-unity (PU) formulation and produces lower error at all tested grid sizes.

Abstract

Signed distance fields (SDFs) are a popular implicit representation of geometry. Converting a discrete set of SDF samples into an explicit surface is a fundamental problem in geometry processing. Traditional reconstruction methods such as marching cubes and dual contouring ignore the geometric information carried by samples far from the surface. Recently, Sellán et al. [2023] and several follow-up works leveraged the tangent-sphere structure of SDFs; every sample implies a point on a sphere tangent to the surface. However, these approaches extract the zero-level set via surface reconstruction, which considers only points and normals on the surface and ignores the remaining samples. We propose an approach that marries the tangent-sphere observation with radial basis function interpolation of all data, the implied surface points and the original data. By detecting spheres with extremely constrained tangent points, a configuration geometrically forced at sharp surface features, we identify and preserve surface corners that surface reconstruction-based methods systematically round. A partition-of-unity decomposition allows our method to scale efficiently to large grid resolutions. Our reconstructions improve both Chamfer and Hausdorff accuracy at every tested resolution.

Fast Forward (20 seconds)

Download as:

BibTeX

(expected)

@article{Cheng:2026:RBFSDF,
 author    = {Cheng, Yong and Gingold, Yotam},
 title     = {{RBF} {Your} {SDF}: {Radial} Basis Function Interpolation of Signed Distance Fields with Implied Tangent Points},
 year      = {2026},
 booktitle = {SIGGRAPH Asia 2026 Conference Proceedings},
 series    = {SA '26},
 keywords  = {Implicit surface reconstruction, Signed Distance Fields, Radial Basis Functions, Sharp features},
}