3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
- URL: http://arxiv.org/abs/2411.07740v1
- Date: Tue, 12 Nov 2024 12:04:44 GMT
- Title: 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
- Authors: Liyuan Zhang, Le Hui, Qi Liu, Bo Li, Yuchao Dai,
- Abstract summary: We propose a powerful 3D focusing-and-matching network for multi-instance point cloud registration.
By using self-attention and cross-attention, we can locate potential matching instances by regressing object centers.
Our method achieves a new state-of-the-art performance on the multi-instance point cloud registration task.
- Score: 45.579241614565376
- License:
- Abstract: Multi-instance point cloud registration aims to estimate the pose of all instances of a model point cloud in the whole scene. Existing methods all adopt the strategy of first obtaining the global correspondence and then clustering to obtain the pose of each instance. However, due to the cluttered and occluded objects in the scene, it is difficult to obtain an accurate correspondence between the model point cloud and all instances in the scene. To this end, we propose a simple yet powerful 3D focusing-and-matching network for multi-instance point cloud registration by learning the multiple pair-wise point cloud registration. Specifically, we first present a 3D multi-object focusing module to locate the center of each object and generate object proposals. By using self-attention and cross-attention to associate the model point cloud with structurally similar objects, we can locate potential matching instances by regressing object centers. Then, we propose a 3D dual masking instance matching module to estimate the pose between the model point cloud and each object proposal. It performs instance mask and overlap mask masks to accurately predict the pair-wise correspondence. Extensive experiments on two public benchmarks, Scan2CAD and ROBI, show that our method achieves a new state-of-the-art performance on the multi-instance point cloud registration task. Code is available at https://github.com/zlynpu/3DFMNet.
Related papers
- Self-supervised 3D Point Cloud Completion via Multi-view Adversarial Learning [61.14132533712537]
We propose MAL-SPC, a framework that effectively leverages both object-level and category-specific geometric similarities to complete missing structures.
Our MAL-SPC does not require any 3D complete supervision and only necessitates a single partial point cloud for each object.
arXiv Detail & Related papers (2024-07-13T06:53:39Z) - Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes [15.706413763407056]
We propose MIRETR, a coarse-to-fine approach to the extraction of instance-aware correspondences.
MIRETR outperforms the state of the arts by 16.6 points on F1 score on the challenging ROBI benchmark.
arXiv Detail & Related papers (2024-04-06T08:51:07Z) - PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest [65.48057241587398]
PoIFusion is a framework to fuse information of RGB images and LiDAR point clouds at the points of interest (PoIs)
Our approach maintains the view of each modality and obtains multi-modal features by computation-friendly projection and computation.
We conducted extensive experiments on nuScenes and Argoverse2 datasets to evaluate our approach.
arXiv Detail & Related papers (2024-03-14T09:28:12Z) - Multi-Model 3D Registration: Finding Multiple Moving Objects in
Cluttered Point Clouds [23.923838486208524]
We investigate a variation of the 3D registration problem, named multi-model 3D registration.
In the multi-model registration problem, we are given two point clouds picturing a set of objects at different poses.
We want to simultaneously reconstruct how all objects moved between the two point clouds.
arXiv Detail & Related papers (2024-02-16T18:01:43Z) - Variational Relational Point Completion Network for Robust 3D
Classification [59.80993960827833]
Vari point cloud completion methods tend to generate global shape skeletons hence lack fine local details.
This paper proposes a variational framework, point Completion Network (VRCNet) with two appealing properties.
VRCNet shows great generalizability and robustness on real-world point cloud scans.
arXiv Detail & Related papers (2023-04-18T17:03:20Z) - OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point
Clouds [4.709764624933227]
We propose the first unsupervised method, called OGC, to simultaneously identify multiple 3D objects in a single forward pass.
We extensively evaluate our method on five datasets, demonstrating the superior performance for object part instance segmentation.
arXiv Detail & Related papers (2022-10-10T07:01:08Z) - Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding [80.04281842702294]
We introduce the concept of the multi-view point cloud (Voint cloud) representing each 3D point as a set of features extracted from several view-points.
This novel 3D Voint cloud representation combines the compactness of 3D point cloud representation with the natural view-awareness of multi-view representation.
We deploy a Voint neural network (VointNet) with a theoretically established functional form to learn representations in the Voint space.
arXiv Detail & Related papers (2021-11-30T13:08:19Z) - 3D Object Classification on Partial Point Clouds: A Practical
Perspective [91.81377258830703]
A point cloud is a popular shape representation adopted in 3D object classification.
This paper introduces a practical setting to classify partial point clouds of object instances under any poses.
A novel algorithm in an alignment-classification manner is proposed in this paper.
arXiv Detail & Related papers (2020-12-18T04:00:56Z)
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.