A Noninvasive Method to Reduce Radiotherapy Positioning Error Caused by Respiration for Patients With Abdominal or Pelvic Cancers

Liu, Weifeng; Jiang, Zhuoran; Chu, Kaiyue; Jin, Jianhua; Ge, Yun; Cai, Jing

doi:10.1177/1533033819825865

Cited by 6 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rigid point cloud registration aims at determining the optimal transformation to align two partially overlapping point clouds into one coherent coordinate system [21,[30][31][32]. This task dominates the performance of systems in many areas, such as robotics [58], augmented reality [6], autonomous driving [35,43], radiotherapy [27], etc. Recent advances have been monopolized by learning-based approaches due to the development of 3D point cloud representation learning and differentiable optimization [38].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

Mei¹,

Tang²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial overlaps. Specifically, we first adopt a network to learn posterior probability distributions of Gaussian mixture models (GMMs) from point clouds. To handle partial point cloud registration, we apply the Sinkhorn algorithm to predict the distribution-level correspondences under the constraint of the mixing weights of GMMs. To enable unsupervised learning, we design three distribution consistencybased losses: self-consistency, cross-consistency, and local contrastive. The self-consistency loss is formulated by encouraging GMMs in Euclidean and feature spaces to share identical posterior distributions. The cross-consistency loss derives from the fact that the points of two partially overlapping point clouds belonging to the same clusters share the cluster centroids. The cross-consistency loss allows the network to flexibly learn a transformation-invariant posterior distribution of two aligned point clouds. The local contrastive loss facilitates the network to extract discriminative local features. Our UDPReg achieves competitive performance on the 3DMatch/3DLoMatch and Model-Net/ModelLoNet benchmarks.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

Mei¹,

Tang²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…P OINT cloud registration is to align two or more 3D point clouds acquired from various views, platforms, or at different times into a unified coordinate system [1]. This technique is the cornerstone of many 3D computer vision applications, such as 3D reconstruction [2], augmenting reality [3], autonomous driving [4], [5], [6], cancer radiotherapy [7], [8] and robotics [9], [10].…”

Section: Introductionmentioning

confidence: 99%

COTReg:Coupled Optimal Transport based Point Cloud Registration

Mei¹,

Huang²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration. This paper proposes a learning framework COTReg by jointly considering the pointwise and structural matchings to predict correspondences of 3D point cloud registration. Specifically, we transform the two matchings into a Wasserstein distance-based and a Gromov-Wasserstein distance-based optimizations, respectively. Thus the task of establishing the correspondences can be naturally reshaped to a coupled optimal transport problem. Furthermore, we design a network to predict the confidence score of being an inlier for each point of the point clouds, which provides the overlap region information to generate correspondences. Our correspondence prediction pipeline can be easily integrated into either learning-based features like FCGF or traditional descriptors like FPFH. We conducted comprehensive experiments on 3DMatch, KITTI, 3DCSR, and ModelNet40 benchmarks, showing the state-of-art performance of the proposed method.

show abstract

Robust real-world point cloud registration by inlier detection

Huang¹,

Wang

et al. 2022

Computer Vision and Image Understanding

View full text Add to dashboard Cite

A Noninvasive Method to Reduce Radiotherapy Positioning Error Caused by Respiration for Patients With Abdominal or Pelvic Cancers

Cited by 6 publications

References 15 publications

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

COTReg:Coupled Optimal Transport based Point Cloud Registration

Robust real-world point cloud registration by inlier detection

Contact Info

Product

Resources

About