Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RINO: Rotation-Invariant Non-Rigid Correspondences

About

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.

Maolin Gao, Shao Jie Hu-Chen, Congyue Deng, Riccardo Marin, Leonidas Guibas, Daniel Cremers• 2026

Related benchmarks

TaskDatasetResultRank
Non-isometric 3D shape matchingSMAL
Mean Geodesic Error4.6
58
Shape MatchingSHREC HOLES 2016 (test)
Average Geodesic Error12.09
26
Shape MatchingFaust
Geodesic Error1.6
21
Shape MatchingSMAL remeshed (test)
Mean Geodesic Error (x100)4.6
20
Non-isometric Shape MatchingDT4D (test)
Mean Geometric Error5.3
14
Raw scan matchingFSCAN (test)
Mean Geometric Error2.5
12
Non-rigid shape matchingSMAL SO(3)
mGeoErr4.6
7
Non-rigid shape matchingSMAL (I/I)
mGeoErr4.6
7
3D shape matchingFAUST (test)
Geodesic Error (E)1.6
6
3D shape matchingSCAPE (test)
E Error2
6
Showing 10 of 13 rows

Other info

Follow for update