SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency
Finding shortest paths on product spaces is a popular approach to tackle numerous variants
of matching problems including the dynamic time warping method for matching signals the …
of matching problems including the dynamic time warping method for matching signals the …
Bijective upsampling and learned embedding for point clouds correspondences
In this paper, we present a novel pipeline to compute and refine a data-driven solution for
estimating the correspondence between 3D point clouds. Our method is compatible with the …
estimating the correspondence between 3D point clouds. Our method is compatible with the …
Non-Rigid Shape Registration via Deep Functional Maps Prior
In this paper, we propose a learning-based framework for non-rigid shape registra-tion
without correspondence supervision. Traditional shape registration techniques typically rely …
without correspondence supervision. Traditional shape registration techniques typically rely …
Non-rigid shape registration via deep functional maps prior
In this paper, we propose a learning-based framework for non-rigid shape registration
without correspondence supervision. Traditional shape registration techniques typically rely …
without correspondence supervision. Traditional shape registration techniques typically rely …
Fast discrete optimisation for geometrically consistent 3d shape matching
In this work we propose to combine the advantages of learning-based and combinatorial
formalisms for 3D shape matching. While learning-based shape matching solutions lead to …
formalisms for 3D shape matching. While learning-based shape matching solutions lead to …
Unsupervised Non-Rigid Point Cloud Matching through Large Vision Models
In this paper, we propose a novel learning-based framework for non-rigid point cloud
matching, which can be trained purely on point clouds without any correspondence …
matching, which can be trained purely on point clouds without any correspondence …
NF-ICP: Neural Field ICP for Robust 3D Human Registration
R Marin, E Corona, G Pons-Moll - openreview.net
Aligning a template to 3D human point clouds is a long-standing problem crucial for tasks
like animation, reconstruction, and most supervised learning pipelines. Recent data-driven …
like animation, reconstruction, and most supervised learning pipelines. Recent data-driven …