Residual Primitive Fitting of 3D Shapes with SuperFrusta

TL;DR

This paper presents SuperFrustum, a new primitive for 3D shape modeling, and ResFit, an iterative algorithm that efficiently decomposes shapes into accurate, editable primitive assemblies, achieving state-of-the-art results.

Contribution

Introduction of SuperFrustum primitives and ResFit algorithm for improved 3D shape decomposition into parsimonious, editable assemblies.

Findings

Achieves over 9 points higher IoU on benchmarks.

Uses nearly half as many primitives as previous methods.

Produces high-fidelity, editable shape programs.

Abstract

We introduce a framework for converting 3D shapes into compact and editable assemblies of analytic primitives, directly addressing the persistent trade-off between reconstruction fidelity and parsimony. Our approach combines two key contributions: a novel primitive, termed SuperFrustum, and an iterative fiting algorithm, Residual Primitive Fitting (ResFit). SuperFrustum is an analytical primitive that is simultaneously (1) expressive, being able to model various common solids such as cylinders, spheres, cones & their tapered and bent forms, (2) editable, being compactly parameterized with 8 parameters, and (3) optimizable, with a sign distance field differentiable w.r.t. its parameters almost everywhere. ResFit is an unsupervised procedure that interleaves global shape analysis with local optimization, iteratively fitting primitives to the unexplained residual of a shape to discover a parsimonious yet accurate decompositions for each input shape. On diverse 3D benchmarks, our method achieves state-of-the-art results, improving IoU by over 9 points while using nearly half as many primitives as prior work. The resulting assemblies bridge the gap between dense 3D data and human-controllable design, producing high-fidelity and editable shape programs.