paper-with-me

Papers

A Convolutional Autoencoder Approach to Learn Volumetric Shape Representations for Brain Structures

2018-10-17 · Evan M. Yu, Mert R. Sabuncu

We propose a novel machine learning strategy for studying neuroanatomical shape variation. Our model works with volumetric binary segmentation images, and requires no pre-processing such as the extraction of surface points or a mesh. The learned shape descriptor is invariant to affine transformations, including shifts, rotations and scaling. Thanks to the adopted autoencoder framework, inter-subject differences are automatically enhanced in the learned representation, while intra-subject variances are minimized. Our experimental results on a shape retrieval task showed that the proposed representation outperforms a state-of-the-art benchmark for brain structures extracted from MRI scans.

📄 PDF Abstract BibTeX arXiv:1810.07746

Code (1)

evanmy/voxel_shape_analysis 공식 구현 pytorch

Tasks

BIG-bench Machine LearningRetrieval

Similar Papers 제목 키워드 기반

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs

2017-03-28 · ICCV 2017 10 · Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox

We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation. The network learns to predict both the structure o…

3D ReconstructionDecoderVocal Bursts Intensity Prediction

Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling

2018-07-04 · ECCV 2018 9 · Matthew Trumble, Andrew Gilbert, Adrian Hilton, John Collomosse

We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder with a dual loss that enforces learning of a …

3D Human Pose EstimationPose Estimation

Cluster-Based Autoencoders for Volumetric Point Clouds

2022-11-02 · Stephan Antholzer, Martin Berger, Tobias Hell

Autoencoders allow to reconstruct a given input from a small set of parameters. However, the input size is often limited due to computational costs. We therefore propose a clustering and reassembling method for volumetri…

Clustering

Cryo-SWAN: the Multi-Scale Wavelet-decomposition-inspired Autoencoder Network for molecular density representation of molecular volumes

2026-02-18 · Rui Li, Artsemi Yushkevich, Mikhail Kudryashev, Artur Yakimovich arxiv

Learning robust representations of 3D shapes from voxelized data is essential for advancing AI methods in biomedical imaging. However, most contemporary 3D computer vision approaches operate on point clouds, meshes, or o…

Point Clouds

VConv-DAE: Deep Volumetric Shape Learning Without Object Labels

2016-04-13 · Abhishek Sharma, Oliver Grau, Mario Fritz

With the advent of affordable depth sensors, 3D capture becomes more and more ubiquitous and already has made its way into commercial products. Yet, capturing the geometry or complete shapes of everyday objects using sca…

DenoisingObject