PointVoxelFormer -- Reviving point cloud networks for 3D medical imaging

• URL: http://arxiv.org/abs/2412.17390v1
• Date: Mon, 23 Dec 2024 08:43:39 GMT
• Title: PointVoxelFormer -- Reviving point cloud networks for 3D medical imaging
• Authors: Mattias Paul Heinrich,
• Abstract summary: Point clouds are a very efficient way to represent volumetric data in medical imaging. Despite their benefits, point clouds are still underexplored in medical imaging compared to volumetric 3D CNNs and vision transformers. This work presents a hybrid approach that combines point-wise operations with intermediate differentiableisation and dense localised CNNs.
• Score: 0.0
• License:
• Abstract: Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D convolutional networks (CNNs) - leading to smaller and robust models. Second, they provide a modality agnostic representation of anatomical surfaces and shapes to avoid domain gaps for generic geometric models. Third, they remove identifiable patient-specific information and may increase privacy preservation when publicly sharing data. Despite their benefits, point clouds are still underexplored in medical imaging compared to volumetric 3D CNNs and vision transformers. To date both datasets and stringent studies on comparative strengths and weaknesses of methodological choices are missing. Interactions and information exchange of spatially close points - e.g. through k-nearest neighbour graphs in edge convolutions or point transformations - within points clouds are crucial for learning geometrically meaningful features but may incur computational bottlenecks. This work presents a hybrid approach that combines point-wise operations with intermediate differentiable rasterisation and dense localised CNNs. For deformable point cloud registration, we devise an early fusion scheme for coordinate features that joins both clouds within a common reference frame and is coupled with an inverse consistent, two-step alignment architecture. Our extensive experiments on three different datasets for segmentation and registration demonstrate that our method, PointVoxelFormer, enables very compact models that excel with threefold speed-ups, fivefold memory reduction and over 30% registration error reduction against edge convolutions and other state-of-the-art models in geometric deep learning.

Related papers

• Fully-Geometric Cross-Attention for Point Cloud Registration [51.865371511201765]
  Point cloud registration approaches often fail when the overlap between point clouds is low due to noisy point correspondences. This work introduces a novel cross-attention mechanism tailored for Transformer-based architectures that tackles this problem. We integrate the Gromov-Wasserstein distance into the cross-attention formulation to jointly compute distances between points across different point clouds. At the point level, we also devise a self-attention mechanism that aggregates the local geometric structure information into point features for fine matching.
  arXiv  Detail & Related papers  (2025-02-12T10:44:36Z)
• Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentation [15.881442863961531]
  We introduce a novel scheme for induced geometric invariance of point cloud representations across domains. On one hand, a novel pretext task of predicting translation of distances of augmented samples is proposed to alleviate centroid shift of point clouds. On the other hand, we pioneer an integration of the relational self-supervised learning on geometrically-augmented point clouds.
  arXiv  Detail & Related papers  (2024-09-11T02:39:19Z)
• Clustering based Point Cloud Representation Learning for 3D Analysis [80.88995099442374]
  We propose a clustering based supervised learning scheme for point cloud analysis. Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space. Our algorithm shows notable improvements on famous point cloud segmentation datasets.
  arXiv  Detail & Related papers  (2023-07-27T03:42:12Z)
• MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis [4.947552172739438]
  We introduce a novel Multi-level Graph Convolution Neural (MLGCN) model, which uses Graph Neural Networks (GNN) blocks to extract features from 3D point clouds at specific locality levels. Our approach produces comparable results to those of state-of-the-art models while requiring up to a thousand times fewer floating-point operations (FLOPs) and having significantly reduced storage requirements.
  arXiv  Detail & Related papers  (2023-03-31T00:15:22Z)
• Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding [61.30276576646909]
  We propose an augmentation-free unsupervised approach for point clouds to learn transferable point-level features via soft clustering, named SoftClu. We exploit the affiliation of points to their clusters as a proxy to enable self-training through a pseudo-label prediction task.
  arXiv  Detail & Related papers  (2022-10-06T10:18:16Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation [81.02742110604161]
  State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern. Our method achieves the 1st place in the leaderboard of Semantic KITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%.
  arXiv  Detail & Related papers  (2020-11-19T18:53:11Z)
• Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions [43.1279121348315]
  We investigate the use of Approximate Convex Decompositions (ACD) as a self-supervisory signal for label-efficient learning of point cloud representations. We show that using ACD to approximate ground truth segmentation provides excellent self-supervision for learning 3D point cloud representations.
  arXiv  Detail & Related papers  (2020-03-30T21:44:43Z)

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.