HandCT: hands-on computational dataset for X-Ray Computed Tomography and
Machine-Learning
- URL: http://arxiv.org/abs/2304.14412v1
- Date: Mon, 17 Apr 2023 13:26:28 GMT
- Title: HandCT: hands-on computational dataset for X-Ray Computed Tomography and
Machine-Learning
- Authors: Emilien Valat, Loth Valat
- Abstract summary: We develop a 3D procedural dataset in order to produce samples for data-driven algorithms.
It is made of a meshed model of a left hand and a script to randomly change its anatomic properties and pose.
This open-source solution relies on the freeware Blender and its Python core.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Machine-learning methods rely on sufficiently large dataset to learn data
distributions. They are widely used in research in X-Ray Computed Tomography,
from low-dose scan denoising to optimisation of the reconstruction process. The
lack of datasets prevents the scalability of these methods to realistic 3D
problems. We develop a 3D procedural dataset in order to produce samples for
data-driven algorithms. It is made of a meshed model of a left hand and a
script to randomly change its anatomic properties and pose whilst conserving
realistic features. This open-source solution relies on the freeware Blender
and its Python core. Blender handles the modelling, the mesh and the generation
of the hand's pose, whilst Python processes file format conversion from obj
file to matrix and functions to scale and center the volume for further
processing. Dataset availability and quality drives research in
machine-learning. We design a dataset that weighs few megabytes, provides
truthful samples and proposes continuous enhancements using version control. We
anticipate this work to be a starting point for anatomically accurate
procedural datasets. For instance, by adding more internal features and fine
tuning their X-Ray attenuation properties.
Related papers
- DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data [50.164670363633704]
We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets from text prompts.
Our model is directly trained on extensive noisy and unaligned in-the-wild' 3D assets.
We achieve state-of-the-art performance in both single-class generation and text-to-3D generation.
arXiv Detail & Related papers (2024-06-06T17:58:15Z) - Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds [45.87961177297602]
This work aims to integrate recent methods into a comprehensive framework for robotic interaction and manipulation in human-centric environments.
Specifically, we leverage 3D reconstructions from a commodity 3D scanner for open-vocabulary instance segmentation.
We show the performance and robustness of our model in two sets of real-world experiments including dynamic object retrieval and drawer opening.
arXiv Detail & Related papers (2024-04-18T18:01:15Z) - LiteNeXt: A Novel Lightweight ConvMixer-based Model with Self-embedding Representation Parallel for Medical Image Segmentation [2.0901574458380403]
We propose a new lightweight but efficient model, namely LiteNeXt, for medical image segmentation.
LiteNeXt is trained from scratch with small amount of parameters (0.71M) and Giga Floating Point Operations Per Second (0.42).
arXiv Detail & Related papers (2024-04-04T01:59:19Z) - MSFormer: A Skeleton-multiview Fusion Method For Tooth Instance
Segmentation [21.38426537318511]
This paper introduces MSFormer, a novel method for tooth segmentation with limited data.
MSFormer incorporates two lightweight modules into existing multiview-based models.
Experiments reveal that MSFormer achieves state-of-the-art performance, requiring only 100 training meshes.
arXiv Detail & Related papers (2023-10-23T01:46:22Z) - 3D Adversarial Augmentations for Robust Out-of-Domain Predictions [115.74319739738571]
We focus on improving the generalization to out-of-domain data.
We learn a set of vectors that deform the objects in an adversarial fashion.
We perform adversarial augmentation by applying the learned sample-independent vectors to the available objects when training a model.
arXiv Detail & Related papers (2023-08-29T17:58:55Z) - Video Pretraining Advances 3D Deep Learning on Chest CT Tasks [63.879848037679224]
Pretraining on large natural image classification datasets has aided model development on data-scarce 2D medical tasks.
These 2D models have been surpassed by 3D models on 3D computer vision benchmarks.
We show video pretraining for 3D models can enable higher performance on smaller datasets for 3D medical tasks.
arXiv Detail & Related papers (2023-04-02T14:46:58Z) - Learning 3D Human Pose Estimation from Dozens of Datasets using a
Geometry-Aware Autoencoder to Bridge Between Skeleton Formats [80.12253291709673]
We propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks.
Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model.
arXiv Detail & Related papers (2022-12-29T22:22:49Z) - RandomRooms: Unsupervised Pre-training from Synthetic Shapes and
Randomized Layouts for 3D Object Detection [138.2892824662943]
A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets.
Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications.
In this work, we put forward a new method called RandomRooms to accomplish this objective.
arXiv Detail & Related papers (2021-08-17T17:56:12Z) - Learning Feature Aggregation for Deep 3D Morphable Models [57.1266963015401]
We propose an attention based module to learn mapping matrices for better feature aggregation across hierarchical levels.
Our experiments show that through the end-to-end training of the mapping matrices, we achieve state-of-the-art results on a variety of 3D shape datasets.
arXiv Detail & Related papers (2021-05-05T16:41:00Z) - Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation [18.76436457395804]
Multi-organ segmentation is one of most successful applications of deep learning in medical image analysis.
Deep convolutional neural nets (CNNs) have shown great promise in achieving clinically applicable image segmentation performance on CT or MRI images.
We propose a new framework for combining 3D and 2D models, in which the segmentation is realized through high-resolution 2D convolutions.
arXiv Detail & Related papers (2020-12-16T21:39:53Z) - Towards General Purpose Geometry-Preserving Single-View Depth Estimation [1.9573380763700712]
Single-view depth estimation (SVDE) plays a crucial role in scene understanding for AR applications, 3D modeling, and robotics.
Recent works have shown that a successful solution strongly relies on the diversity and volume of training data.
Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry.
arXiv Detail & Related papers (2020-09-25T20:06:13Z)
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.