Landmark-free Statistical Shape Modeling via Neural Flow Deformations
- URL: http://arxiv.org/abs/2209.06861v1
- Date: Wed, 14 Sep 2022 18:17:19 GMT
- Title: Landmark-free Statistical Shape Modeling via Neural Flow Deformations
- Authors: David L\"udke, Tamaz Amiranashvili, Felix Ambellan, Ivan Ezhov, Bjoern
Menze, Stefan Zachow
- Abstract summary: We present FlowSSM, a novel shape modeling approach that learns shape variability without requiring dense correspondence between training instances.
Our model outperforms state-of-the-art methods in providing an expressive and robust shape prior for distal femur and liver.
- Score: 0.5897108307012394
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Statistical shape modeling aims at capturing shape variations of an
anatomical structure that occur within a given population. Shape models are
employed in many tasks, such as shape reconstruction and image segmentation,
but also shape generation and classification. Existing shape priors either
require dense correspondence between training examples or lack robustness and
topological guarantees. We present FlowSSM, a novel shape modeling approach
that learns shape variability without requiring dense correspondence between
training instances. It relies on a hierarchy of continuous deformation flows,
which are parametrized by a neural network. Our model outperforms
state-of-the-art methods in providing an expressive and robust shape prior for
distal femur and liver. We show that the emerging latent representation is
discriminative by separating healthy from pathological shapes. Ultimately, we
demonstrate its effectiveness on two shape reconstruction tasks from partial
data. Our source code is publicly available
(https://github.com/davecasp/flowssm).
Related papers
- Deep Medial Voxels: Learned Medial Axis Approximations for Anatomical Shape Modeling [5.584193645582203]
We introduce deep medial voxels, a semi-implicit representation that faithfully approximates the topological skeleton from imaging volumes.
Our reconstruction technique shows potential for both visualization and computer simulations.
arXiv Detail & Related papers (2024-03-18T13:47:18Z) - 3D Shape Completion on Unseen Categories:A Weakly-supervised Approach [61.76304400106871]
We introduce a novel weakly-supervised framework to reconstruct the complete shapes from unseen categories.
We first propose an end-to-end prior-assisted shape learning network that leverages data from the seen categories to infer a coarse shape.
In addition, we propose a self-supervised shape refinement model to further refine the coarse shape.
arXiv Detail & Related papers (2024-01-19T09:41:09Z) - Implicit Shape Modeling for Anatomical Structure Refinement of
Volumetric Medical Images [29.894934602946567]
We propose a unified framework for 3D shape modelling and segmentation refinement based on implicit neural networks.
For improved shape representation, implicit shape constraints are used for both instances and latent templates.
Experiments on validation datasets involving liver, pancreas and lung segmentation demonstrate the superiority of our approach.
arXiv Detail & Related papers (2023-12-11T07:09:32Z) - Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy [0.0]
We propose Mesh2SSM, a new approach that leverages unsupervised, permutation-invariant representation learning to estimate how to deform a template point cloud to subject-specific meshes.
Mesh2SSM can also learn a population-specific template, reducing any bias due to template selection.
arXiv Detail & Related papers (2023-05-13T00:03:59Z) - OCD: Learning to Overfit with Conditional Diffusion Models [95.1828574518325]
We present a dynamic model in which the weights are conditioned on an input sample x.
We learn to match those weights that would be obtained by finetuning a base model on x and its label y.
arXiv Detail & Related papers (2022-10-02T09:42:47Z) - Topology-Preserving Shape Reconstruction and Registration via Neural
Diffeomorphic Flow [22.1959666473906]
Deep Implicit Functions (DIFs) represent 3D geometry with continuous signed distance functions learned through deep neural nets.
We propose a new model called Neural Diffeomorphic Flow (NDF) to learn deep implicit shape templates.
NDF achieves consistently state-of-the-art organ shape reconstruction and registration results in both accuracy and quality.
arXiv Detail & Related papers (2022-03-16T14:39:11Z) - Augmenting Implicit Neural Shape Representations with Explicit
Deformation Fields [95.39603371087921]
Implicit neural representation is a recent approach to learn shape collections as zero level-sets of neural networks.
We advocate deformation-aware regularization for implicit neural representations, aiming at producing plausible deformations as latent code changes.
arXiv Detail & Related papers (2021-08-19T22:07:08Z) - NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One
Go [109.88509362837475]
We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes.
NeuroMorph produces smooth and point-to-point correspondences between them.
It works well for a large variety of input shapes, including non-isometric pairs from different object categories.
arXiv Detail & Related papers (2021-06-17T12:25:44Z) - Discriminative and Generative Models for Anatomical Shape Analysison
Point Clouds with Deep Neural Networks [3.7814216736076434]
We introduce deep neural networks for the analysis of anatomical shapes that learn a low-dimensional shape representation from the given task.
Our framework is modular and consists of several computing blocks that perform fundamental shape processing tasks.
We propose a discriminative model for disease classification and age regression, as well as a generative model for the accruate reconstruction of shapes.
arXiv Detail & Related papers (2020-10-02T07:37:40Z) - Shape Prior Deformation for Categorical 6D Object Pose and Size
Estimation [62.618227434286]
We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image.
We propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior.
arXiv Detail & Related papers (2020-07-16T16:45:05Z) - Monocular Human Pose and Shape Reconstruction using Part Differentiable
Rendering [53.16864661460889]
Recent works succeed in regression-based methods which estimate parametric models directly through a deep neural network supervised by 3D ground truth.
In this paper, we introduce body segmentation as critical supervision.
To improve the reconstruction with part segmentation, we propose a part-level differentiable part that enables part-based models to be supervised by part segmentation.
arXiv Detail & Related papers (2020-03-24T14:25:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.