Deep graph-based spatial consistency for robust non-rigid point cloud registration

Z Qin, H Yu, C Wang, Y Peng… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
We study the problem of outlier correspondence pruning for non-rigid point cloud
registration. In rigid registration, spatial consistency has been a commonly used criterion to …

Spatially and spectrally consistent deep functional maps

M Sun, S Mao, P Jiang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Cycle consistency has long been exploited as a powerful prior for jointly optimizing maps
within a collection of shapes. In this paper, we investigate its utility in the approaches of …

Spectral meets spatial: Harmonising 3d shape matching and interpolation

D Cao, M Eisenberger, N El Amrani… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Although 3D shape matching and interpolation are highly interrelated they are often studied
separately and applied sequentially to relate different 3D shapes thus resulting in sub …

Smooth non-rigid shape matching via effective dirichlet energy optimization

R Magnet, J Ren, O Sorkine-Hornung… - … Conference on 3D …, 2022‏ - ieeexplore.ieee.org
We introduce pointwise map smoothness via the Dirich-let energy into the functional map
pipeline, and propose an algorithm for optimizing it efficiently, which leads to highquality …

Robust zero level-set extraction from unsigned distance fields based on double covering

F Hou, X Chen, W Wang, H Qin, Y He - ACM Transactions on Graphics …, 2023‏ - dl.acm.org
In this paper, we propose a new method, called DoubleCoverUDF, for extracting the zero
level-set from unsigned distance fields (UDFs). DoubleCoverUDF takes a learned UDF and …

Generalizing neural human fitting to unseen poses with articulated se (3) equivariance

H Feng, P Kulits, S Liu, MJ Black… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
We address the problem of fitting a parametric human body model (SMPL) to point cloud
data. Optimization based methods require careful initialization and are prone to becoming …

Spidermatch: 3d shape matching with global optimality and geometric consistency

P Roetzer, F Bernard - … of the IEEE/CVF Conference on …, 2024‏ - openaccess.thecvf.com
Finding shortest paths on product spaces is a popular approach to tackle numerous variants
of matching problems including the dynamic time war** method for matching signals the …

Memory-scalable and simplified functional map learning

R Magnet, M Ovsjanikov - … of the IEEE/CVF Conference on …, 2024‏ - openaccess.thecvf.com
Deep functional maps have emerged in recent years as a prominent learning-based
framework for non-rigid shape matching problems. While early methods in this domain only …

Ccuantumm: Cycle-consistent quantum-hybrid matching of multiple shapes

H Bhatia, E Tretschk, Z Lähner… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Jointly matching multiple, non-rigidly deformed 3D shapes is a challenging, NP-hard
problem. A perfect matching is necessarily cycle-consistent: Following the pairwise point …

Correspondence-free non-rigid point set registration using unsupervised clustering analysis

M Zhao, J Jiang, L Ma, S **n… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
This paper presents a novel non-rigid point set registration method that is inspired by
unsupervised clustering analysis. Unlike previous approaches that treat the source and …