Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures
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.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object RecognitionObject RecognitionSimilar Papers 제목 키워드 기반
A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras
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 RegistrationModeling Urban Scenes From Pointclouds
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 SegmentationA Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution Detection
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) DetectionTango3D: Towards Alignment for Global and Local 2D-3D Correspondence
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 CloudsPointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
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