Unified Primitive Proxies for Structured Shape Completion

Zhaiyu Chen1,2, Yuqing Wang1, Xiao Xiang Zhu1,2
1Technical University of Munich, 2Munich Center for Machine Learning

Paper Code Colab Demo
UniCo teaser figure

UniCo is a structured shape completion model that, given a partial scan, jointly predicts a complete set of quadratic primitives with geometry, semantics, and inlier membership. The predicted primitives are assembly-ready for surface reconstruction.

Abstract

Structured shape completion recovers missing geometry as primitives rather than as unstructured points, which enables primitive-based surface reconstruction. Instead of following the prevailing cascade, we rethink how primitives and points should interact, and find it more effective to decode primitives in a dedicated pathway that attends to shared shape features. Following this principle, we present UniCo, which in a single feed-forward pass predicts a set of primitives with complete geometry, semantics, and inlier membership. To drive this unified representation, we introduce primitive proxies, learnable queries that are contextualized to produce assembly-ready outputs. To ensure consistent optimization, our training strategy couples primitives and points with online target updates. Across synthetic and real-world benchmarks with four independent assembly solvers, UniCo consistently outperforms recent baselines, lowering Chamfer distance by up to 50% and improving normal consistency by up to 7%. These results establish an attractive recipe for structured 3D understanding from incomplete data.

Comparison with other methods

Drag to rotate, scroll to zoom.

Input
GT
UniCo
Method
Input
GT
UniCo
Method
Robustness

Left: as incompleteness grows from 25% to 75%, UniCo maintains lower CD and higher NC than pointwise baselines. Middle: under the debiased normalization protocol, UniCo remains stable with low pose and scale bias. Right: under Gaussian jitter of 1-3%, performance degrades gracefully.

How it works

UniCo architecture

Shape features from a partial point cloud feed two coordinated pathways. The point pathway decodes dense completed points. The primitive pathway uses primitive proxies that attend to the shared features and predict primitive semantics, geometry, inlier membership, and a confidence score used at inference to select valid primitives.

BibTeX

@article{chen2026unico,
    title={Unified Primitive Proxies for Structured Shape Completion}, 
    author={Zhaiyu Chen and Yuqing Wang and Xiao Xiang Zhu},
    journal={arXiv preprint arXiv:TBD},
    year={2026}
}