Obtaining highly consistent correspondences between point clouds is crucial for computer vision tasks such as 3D registration and recognition. Due to nuisances such as limited overlap and noise, initial correspondences often contain a large number of outliers, imposing a great challenge to downstream tasks. In this paper, we present a novel single voter spreading (SVOS) method for efficient 3D correspondence grouping and 3D registration. Our core insight is to leverage low-order graph constraints only in a single voter spreading voting scheme to achieve comparable constrain-ability as complex constraints without searching them. First, a simple first-order graph is constructed for the initial correspondence set. Second, a two-stage voting method is proposed, including single voter voting and spread voters voting. Each voting stage involves both local and global voting via edge constraints only. This promises good selectivity while making the voting process time- and storage-efficient. Finally, top-scored correspondences are opted for robust transformation estimation. Experiments on U3M, 3DMatch/3DLoMatch, ETH, and KITTI-LC datasets verify that SVOS achieves new state-of-the-art correspondence grouping and registration performance, while being light-weight and robust to graph construction parameters.

As a fundamental problem in computer vision, multi-view stereo (MVS) aims at recovering the 3D geometry of the target from a set of 2D images. However, the reconstructed quality is significantly impacted by the presence of low-textured areas. In this paper, we propose a Hierarchical Prior Mining (HPM) framework for non-local multi-view stereo. Different from most existing works dedicated to focusing on local information and only using a single prior, HPM captures non-local structural cues and leverages multi-source priors for geometry recovery. Based on the framework, we first propose HPM-MVS, which obtains precise initial hypotheses through non-local operations, simultaneously constructing a better planar prior model in an HPM framework to further facilitate hypothesis generation. In addition, we futher propose HPM-MVS++, which excavates the structured region information of images and spatial geometric relationships of hypotheses as prior knowledge. Then, it incorporates them into probabilistic graphical models, ultimately deducing two novel multi-view matching costs. This significantly enhances the robustness to challenging situations and improves the completeness of the reconstruction. Experimental results on the ETH3D and Tanks & Temples have verified the superior performance and strong generalization capability of our approach.

Maximal cliques (MAC) represent a novel state-of-theart approach for 3D registration from correspondences, however, it still suffers from extremely severe outliers. In this paper, we introduce a robust learning-free estimator called MAC++, exploring maximal cliques for$3 D$registration from the following two perspectives: 1)$A$novel hypothesis generation method utilizing putative seeds through voting to guide the construction of maximal clique pools, effectively preserving more potential correct hypotheses. 2) A progressive hypothesis evaluation method that continuously reduces the solution space in a “global-clusters-cluster-individual” manner rather than traditional one-shot techniques, greatly alleviating the issue of missing good hypotheses. Experiments conducted on U3M, 3DMatch/3DLoMatch, and KITTI-LC datasets show the new state-of-the-art performance of MAC++. MAC++ demonstrates the capability to handle extremely low inlier ratio data where MAC fails (e.g., showing 27.1%/30.6% registration recall improvements on 3DMatch/3DLoMatch with$<1 \%$inliers).

In real-world environments, a LiDAR point cloud registration method with robust generalization capabilities (across varying distances and datasets) is crucial for ensuring safety in autonomous driving and other LiDAR-based applications. However, current methods fall short in achieving this level of generalization. To address these limitations, we propose UGP, a pruned framework designed to enhance generalization power for LiDAR point cloud registration. The core insight in UGP is the elimination of cross-attention mechanisms to improve generalization, allowing the network to concentrate on intra-frame feature extraction. Additionally, we introduce a progressive self-attention module to reduce ambiguity in large-scale scenes and integrate Bird’s Eye View (BEV) features to incorporate semantic information about scene elements. Together, these enhancements significantly boost the network’s generalization performance. We validated our approach through various generalization experiments in multiple outdoor scenes. In cross-distance generalization experiments on KITTI and nuScenes, UGP achieved state-of-the-art mean Registration Recall rates of 94.5% and 91.4%, respectively. In cross-dataset generalization from nuScenes to KITTI, UGP achieved a state-of-the-art mean Registration Recall of 90.9%. Code will be available at https://github.com/peakpang/UGP

Geometric constraints between feature matches are critical in 3D point cloud registration problems. Existing approaches typically model unordered matches as a consistency graph and sample consistent matches to generate hypotheses. However, explicit graph construction introduces noise, posing great challenges for handcrafted geometric constraints to render consistency. To overcome this, we propose HyperGCT, a flexible dynamic Hyper-GNN-learned geometric ConstrainT that leverages high-order consistency among 3D correspondences. To our knowledge, HyperGCT is the first method that mines robust geometric constraints from dynamic hypergraphs for 3D registration. By dynamically optimizing the hypergraph through vertex and edge feature aggregation, HyperGCT effectively captures the correlations among correspondences, leading to accurate hypothesis generation. Extensive experiments on 3DMatch, 3DLoMatch, KITTI-LC, and ETH show that HyperGCT achieves state-of-the-art performance. Furthermore, HyperGCT is robust to graph noise, demonstrating a significant advantage in terms of generalization.

Consistent correspondences between point clouds are vital to 3D vision tasks such as registration and recognition. In this paper, we present a mutual voting method for ranking 3D correspondences. The key insight is to achieve reliable scoring results for correspondences by refining both voters and candidates in a mutual voting scheme. First, a graph is constructed for the initial correspondence set with the pairwise compatibility constraint. Second, nodal clustering coefficients are introduced to preliminarily remove a portion of outliers and speed up the following voting process. Third, we model nodes and edges in the graph as candidates and voters, respectively. Mutual voting is then performed in the graph to score correspondences. Finally, the correspondences are ranked based on the voting scores and top-ranked ones are identified as inliers. Feature matching, 3D point cloud registration, and 3D object recognition experiments on various datasets with different nuisances and modalities verify that MV is robust to heavy outliers under different challenging settings, and can significantly boost 3D point cloud registration and 3D object recognition performance.

This paper presents a 3D registration method with maximal cliques (MAC) for 3D point cloud registration (PCR). The key insight is to loosen the previous maximum clique constraint and mine more local consensus information in a graph for accurate pose hypotheses generation: 1) A compatibility graph is constructed to render the affinity relationship between initial correspondences. 2) We search for maximal cliques in the graph, each representing a consensus set. 3) Transformation hypotheses are computed for the selected cliques by the SVD algorithm and the best hypothesis is used to perform registration. In addition, we present a variant of MAC if given overlap prior, called MAC-OP. Overlap prior further enhances MAC from many technical aspects, such as graph construction with re-weighted nodes, hypotheses generation from cliques with additional constraints, and hypothesis evaluation with overlap-aware weights. Extensive experiments demonstrate that both MAC and MAC-OP effectively increase registration recall, outperform various state-of-the-art methods, and boost the performance of deep-learned methods. For instance, MAC combined with GeoTransformer achieves a state-of-the-art registration recall of [Formula: see text] on 3DMatch / 3DLoMatch. We perform synthetic experiments on 3DMatch-LIR / 3DLoMatch-LIR, a dataset with extremely low inlier ratios for 3D registration in ultra-challenging cases.

As a fundamental problem in computer vision, 3D point cloud registration (PCR) aims to seek the optimal pose to align a point cloud pair. In this paper, we present a 3D registration method with maximal cliques (MAC). The key insight is to loosen the previous maximum clique constraint, and mine more local consensus information in a graph for accurate pose hypotheses generation: 1) A compatibility graph is constructed to render the affinity relationship between initial correspondences. 2) We search for maximal cliques in the graph, each of which represents a consensus set. We perform node-guided clique selection then, where each node corresponds to the maximal clique with the greatest graph weight. 3) Transformation hypotheses are computed for the selected cliques by the SVD algorithm and the best hypothesis is used to perform registration. Extensive experiments on U3M, 3DMatch, 3DLoMatch and KITTI demonstrate that MAC effectively increases registration accuracy, outperforms various state-of-the-art methods and boosts the performance of deep-learned methods. MAC combined with deep-learned methods achieves state-of-the-art registration recall of 95.7% /78.9% on 3DMatch /3DLoMatch.