Related papers: UTOPIC: Uncertainty-aware Overlap Prediction Netwo…

Correspondence-based rotation search and point cloud registration are two fundamental problems in robotics and computer vision. However, the presence of outliers, sometimes even occupying the great majority of the putative correspondences,…

Pairwise point cloud registration is a critical task for many applications, which heavily depends on finding correct correspondences from the two point clouds. However, the low overlap between input point clouds causes the registration to…

Unsafe surgical care is a critical health concern, often linked to limitations in surgeon experience, skills, and situational awareness. Integrating patient-specific 3D models into the surgical field can enhance visualization, provide…

In this paper, we introduce a non-rigid registration pipeline for pairs of unorganized point clouds that may be topologically different. Standard warp field estimation algorithms, even under robust, discontinuity-preserving regularization,…

This paper concerns the research problem of point cloud registration to find the rigid transformation to optimally align the source point set with the target one. Learning robust point cloud registration models with deep neural networks has…

Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning methods in this field, spatial consistency, which is…

We present a novel non-iterative learnable method for partial-to-partial 3D shape registration. The partial alignment task is extremely complex, as it jointly tries to match between points and identify which points do not appear in the…

Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (i.e., noise and incompleteness), which is a common issue in…

In this paper, we discuss feature engineering for single-pass uncertainty estimation. For accurate uncertainty estimates, neural networks must extract differences in the feature space that quantify uncertainty. This could be achieved by…

3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature…

Quantification of uncertainty in point cloud matching is critical in many tasks such as pose estimation, sensor fusion, and grasping. Iterative closest point (ICP) is a commonly used pose estimation algorithm which provides a point estimate…

In this paper, we present a novel unpaired point cloud completion network, named Cycle4Completion, to infer the complete geometries from a partial 3D object. Previous unpaired completion methods merely focus on the learning of geometric…

Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape. Previous approaches propose neural networks to directly estimate the whole point cloud through…

Point cloud completion, which aims at recovering original shape information from partial point clouds, has attracted attention on 3D vision community. Existing methods usually succeed in completion for standard shape, while failing to…

We introduce a novel framework for multiway point cloud mosaicking (named Wednesday), designed to co-align sets of partially overlapping point clouds -- typically obtained from 3D scanners or moving RGB-D cameras -- into a unified…

As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better…

Reliable quantification of uncertainty in Mobile Laser Scanning (MLS) point clouds is essential for ensuring the accuracy and credibility of downstream applications such as 3D mapping, modeling, and change analysis. Traditional backward…

Image-to-point cloud registration aims to determine the relative camera pose between an RGB image and a reference point cloud, serving as a general solution for locating 3D objects from 2D observations. Matching individual points with…

The discriminative feature is crucial for point cloud registration. Recent methods improve the feature discriminative by distinguishing between non-overlapping and overlapping region points. However, they still face challenges in…

Visual place recognition methods struggle with occlusions and partial visual overlaps. We propose a novel visual place recognition approach based on overlap prediction, called VOP, shifting from traditional reliance on global image…