Pointview-GCN: 3D Shape Classification With Multi-View Point Clouds

Mohammadi, Seyed; Wang, Yiming; Bue, Alessio Del

doi:10.1109/icip42928.2021.9506426

Cited by 39 publications

(23 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As previously discussed, geometric deep learning is the branch of deep learning that deals with graph or manifold (unstructured) data such as graphs created on point clouds. Geometric deep learning has predominantly been used on point cloud data to produce state-of-the-art results for classification and representation learning tasks [38, 40]. Our model incorporated edge convolution [25] as the primary operator in our encoder part of our autoencoder as this has proved successful in representation learning tasks [55].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

3D single-cell shape analysis using geometric deep learning

Vries

Curry

Rowe-Brown

et al. 2022

Preprint

View full text Add to dashboard Cite

Aberrations in cell geometry are linked to cell signalling and disease. For example, metastatic melanoma cells alter their shape to invade tissues and drive disease. Despite this, there is a paucity of methods to quantify cell shape in 3D and little understanding of the shape-space cells explore. Currently, most descriptions of cell shape rely on predefined measurements of cell regions or points along a perimeter. The adoption of 3D tissue culture and imaging systems in medical research has recently created a growing need for comprehensive 3D shape descriptions of cells. We have addressed this need using unsupervised geometric deep learning to learn shape representations of cells from 3D microscopy images of metastatic melanoma cells embedded in collagen tissue-like matrices. We used a dynamic graph convolutional foldingnet autoencoder with improved deep embedded clustering to simultaneously learn lower-dimensional representations and classes of 3D cell shapes from a dataset of more than 70,000 drug-treated melanoma cells imaged by high throughput light-sheet microscopy. We propose describing cell shape using 3D quantitative morphological signatures, which represent a cell's similarity to shape modes in the dataset, and are a direct output from our model. We used the extracted features to reveal the extent of the cell shape landscape and found that the shapes learned could predict drug treatment (up to 86% accuracy) and cell microenvironment, and are explainable. In particular, we found strikingly similar deep learning shape signatures between cells treated with microtubule polymerisation inhibitors and branched actin inhibitors. Finally, we implemented our methods as a Python package for ease of use by the medical research community.

show abstract

Section: Discussionmentioning

confidence: 99%

“…DL on point cloud data often involves representing point clouds as graphs and then performing geometric deep learning (GDL) on these graphs [25, 36, 27, 37, 38]. In computer science, graphs are data structures that consist of nodes and edges.…”

Section: Introductionmentioning

confidence: 99%

3D single-cell shape analysis using geometric deep learning

Vries

Curry

Rowe-Brown

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…3) Results on ModelNet40 and ScanObjectNN Datasets: We compare our method with the state-of-the-art. Among the MLP and CNN based classification methods, we compare with the PointNet [7], PointNet++ [44], DGCNN [45], Spider-CNN [46], PointCNN [47], and 3DmFV [48]. We also compare with transformer based methods, which include Transformer [27], Transformer+OcCo [49], POS-BERT [28] and NPCT [50].…”

Section: B Classification Taskmentioning

confidence: 99%

Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps

Ibrahim¹,

Akhtar²,

Anwar³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…To apply GCN on the data which naturally has the graph structure seems straightforward, such as graph-based recommendation systems [27], point clouds classification [21], and molecular properties prediction [22], etc. However, the graph nature of some other data may not be so explicit.…”

Section: Gcn On Clusteringmentioning

confidence: 99%

An Efficient Person Clustering Algorithm for Open Checkout-free Groceries

Wu¹,

Fu²,

Liu³

2022

Preprint

View full text Add to dashboard Cite

Open checkout-free grocery is the grocery store where the customers never have to wait in line to check out. Developing a system like this is not trivial since it faces challenges of recognizing the dynamic and massive flow of people. In particular, a clustering method that can efficiently assign each snapshot to the corresponding customer is essential for the system. In order to address the unique challenges in the open checkout-free grocery, we propose an efficient and effective person clustering method. Specifically, we first propose a Crowded Sub-Graph (CSG) to localize the relationship among massive and continuous data streams. CSG is constructed by the proposed Pick-Link-Weight (PLW) strategy, which picks the nodes based on time-space information, links the nodes via trajectory information, and weighs the links by the proposed von Mises-Fisher (vMF) similarity metric. Then, to ensure that the method adapts to the dynamic and unseen person flow, we propose Graph Convolutional Network (GCN) with a simple Nearest Neighbor (NN) strategy to accurately cluster the instances of CSG. GCN is adopted to project the features into low-dimensional separable space, and NN is able to quickly produce a result in this space upon dynamic person flow. The experimental results show that the proposed method outperforms other alternative algorithms in this scenario. In practice, the whole system has been implemented and deployed in several real-world open checkout-free groceries.

show abstract

Pointview-GCN: 3D Shape Classification With Multi-View Point Clouds

Cited by 39 publications

References 14 publications

3D single-cell shape analysis using geometric deep learning

3D single-cell shape analysis using geometric deep learning

Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps

An Efficient Person Clustering Algorithm for Open Checkout-free Groceries

Contact Info

Product

Resources

About