RINO: Rotation-Invariant Non-Rigid Correspondences

2026-03-29

AI Summary

This work addresses the challenge of establishing dense correspondences across complex 3D shapes under non-isometric deformations, partial missing data, non-manifold structures, and arbitrary poses. To this end, we propose an unsupervised, rotation-invariant, end-to-end deep learning framework that operates without pre-alignment or handcrafted features, unifying rigid and non-rigid matching within a single architecture. Our approach innovatively integrates SO(3)-invariant vector learning with orientation-aware complex-valued function mapping to extract features robust to intricate geometric deformations and noise. Built upon the RINONet architecture, the method consistently outperforms state-of-the-art techniques across diverse and challenging non-rigid correspondence tasks, demonstrating exceptional generalization capability and robustness.

Technology Category

Machine Learning: Learning with ManifoldsComputer Vision: 3D Computer VisionIntelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSystems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under non-isometric deformations, partial data, and non-manifold inputs. To overcome these issues, we introduce RINO, an unsupervised, rotation-invariant dense correspondence framework that effectively unifies rigid and non-rigid shape matching. The core of our method is the novel RINONet, a feature extractor that integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry. This allows for a fully end-to-end, data-driven approach that bypasses the need for shape pre-alignment or handcrafted features. Extensive experiments show unprecedented performance of RINO across challenging non-rigid matching tasks, including arbitrary poses, non-isometry, partiality, non-manifoldness, and noise.

Problem

• dense correspondence
• non-rigid deformation
• rotation invariance
• partial data
• non-manifold

Innovation

• rotation-invariant
• non-rigid correspondence
• SO(3)-invariant learning
• functional maps
• unsupervised 3D matching