paper-with-me

홈 › Papers

Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures

2016-03-15 · CVPR 2017 7 · Julian Straub, Trevor Campbell, Jonathan P. How, John W. Fisher III

Point cloud alignment is a common problem in computer vision and robotics, with applications ranging from 3D object recognition to reconstruction. We propose a novel approach to the alignment problem that utilizes Bayesian nonparametrics to describe the point cloud and surface normal densities, and branch and bound (BB) optimization to recover the relative transformation. BB uses a novel, refinable, near-uniform tessellation of rotation space using 4D tetrahedra, leading to more efficient optimization compared to the common axis-angle tessellation. We provide objective function bounds for pruning given the proposed tessellation, and prove that BB converges to the optimum of the cost function along with providing its computational complexity. Finally, we empirically demonstrate the efficiency of the proposed approach as well as its robustness to real-world conditions such as missing data and partial overlap.

📄 PDF Abstract BibTeX arXiv:1603.04868

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object RecognitionObject Recognition

Similar Papers 제목 키워드 기반

A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras

2020-11-10 · Ray Zhang, Tzu-Yuan Lin, Chien Erh Lin, Steven A. Parkison 외

This paper reports on a novel nonparametric rigid point cloud registration framework that jointly integrates geometric and semantic measurements such as color or semantic labels into the alignment process and does not re…

GPUPoint Cloud Registration

Modeling Urban Scenes From Pointclouds

2017-10-01 · ICCV 2017 10 · William Nguatem, Helmut Mayer

We present a method for Modeling Urban Scenes from Pointclouds (MUSP). In contrast to existing approaches, MUSP is robust, scalable and provides a more complete description by not making a Manhattan-World assumption and …

Scene Segmentation

A Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution Detection

2025-02-12 · Randolph W. Linderman, Yiran Chen, Scott W. Linderman

Bayesian nonparametric methods are naturally suited to the problem of out-of-distribution (OOD) detection. However, these techniques have largely been eschewed in favor of simpler methods based on distances between pre-t…

Out-of-Distribution DetectionOut of Distribution (OOD) Detection

Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence

2026-05-19 · Zebin He, Mingxin Yang, Shuhui Yang, Hanxiao Sun 외 arxiv

Existing 3D foundation models typically align point clouds to frozen vision-language spaces like CLIP, which achieve strong cross-modal retrieval by compressing 3D shape into a global vector. However, this global-only al…

Cross-Modal RetrievalPoint Clouds

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation

2019-11-07 · NeurIPS 2019 12 · Can Qin, Haoxuan You, Lichen Wang, C. -C. Jay Kuo 외

Domain Adaptation (DA) approaches achieved significant improvements in a wide range of machine learning and computer vision tasks (i.e., classification, detection, and segmentation). However, as far as we are aware, ther…

Domain AdaptationUnsupervised Domain Adaptation