Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors address problems in matching 3D shapes that bend or partially overlap, where usual methods struggle because the math tools don't line up well. They create a special neural network that predicts more flexible maps between shapes, improving alignment. This new method learns without needing labeled examples and works by adjusting standard maps in a smarter way. Tests show their approach fits well with current systems and improves accuracy in tough cases.
functional maps3D shape matchingnon-rigid shapesspectral baseshyper-networkMLPunsupervised learningspectral alignment losstopological noisepoint clouds
Authors
Dongliang Cao, Florian Bernard
Abstract
Functional maps are the cornerstone of recent non-rigid 3D shape matching methods due to their efficiency and performance. However, existing methods struggle with challenging scenarios, such as partiality, topological noise, and raw point clouds. A primary bottleneck is that significant intrinsic distortion prevents truncated spectral bases from being accurately aligned via linear transformations (i.e., functional maps). To address this, we introduce a hyper-network that predicts non-linear neural functional maps (NFM), learned in an unsupervised manner, to better align spectral bases. Specifically, we model the NFM as an MLP with skip-connection to refine standard FM and employ a hyper-network to predict its weights, conditioned on standard FM. Our framework is trained using a novel unsupervised spectral alignment loss. Experiments demonstrate that our approach can be seamlessly integrated into state-of-the-art unsupervised deep functional map pipelines, substantially improving matching accuracy in demanding scenarios.