paper-with-me

홈 › Papers

Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking

2022-09-14 · Haobo Jiang, Kaihao Lan, Le Hui, Guangyu Li, Jin Xie, Jian Yang

Learning robust feature matching between the template and search area is crucial for 3D Siamese tracking. The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization. In this paper, we propose a novel point cloud registration-driven Siamese tracking framework, with the intuition that spatially aligned corresponding points (via 3D registration) tend to achieve consistent feature representations. Specifically, our method consists of two modules, including a tracking-specific nonlocal registration module and a registration-aided Sinkhorn template-feature aggregation module. The registration module targets at the precise spatial alignment between the template and search area. The tracking-specific spatial distance constraint is proposed to refine the cross-attention weights in the nonlocal module for discriminative feature learning. Then, we use the weighted SVD to compute the rigid transformation between the template and search area, and align them to achieve the desired spatially aligned corresponding points. For the feature aggregation model, we formulate the feature matching between the transformed template and search area as an optimal transport problem and utilize the Sinkhorn optimization to search for the outlier-robust matching solution. Also, a registration-aided spatial distance map is built to improve the matching robustness in indistinguishable regions (e.g., smooth surface). Finally, guided by the obtained feature matching map, we aggregate the target information from the template into the search area to construct the target-specific feature, which is then fed into a CenterPoint-like detection head for object localization. Extensive experiments on KITTI, NuScenes and Waymo datasets verify the effectiveness of our proposed method.

📄 PDF Abstract BibTeX arXiv:2209.06395

Code (0)

등록된 구현이 없습니다.

Tasks

Object LocalizationObject TrackingPoint Cloud Registration

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration

2025-12-10 · Haobo Jiang, Jin Xie, Jian Yang, Liang Yu 외 arxiv

In this paper, we propose a novel 3D registration paradigm, Generative Point Cloud Registration, which bridges advanced 2D generative models with 3D matching tasks to enhance registration performance. Our key idea is to …

Point Cloud RegistrationPoint Clouds

3D Point Cloud Registration with Learning-based Matching Algorithm

2022-02-04 · rintaro yanagi, Atsushi Hashimoto, Shusaku Sone, Naoya Chiba 외

We present a novel differential matching algorithm for 3D point cloud registration. Instead of only optimizing the feature extractor for a matching algorithm, we propose a learning-based matching module optimized to the …

Point Cloud Registration

Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework

2024-12-25 · Guiyu Zhao, Zhentao Guo, Zewen Du, Hongbin Ma

Due to the density inconsistency and distribution difference between cross-source point clouds, previous methods fail in cross-source point cloud registration. We propose a density-robust feature extraction and matching …

Point Cloud Registration

Overlap Bias Matching is Necessary for Point Cloud Registration

2023-08-18 · Pengcheng Shi, Jie Zhang, Haozhe Cheng, Junyang Wang 외

Point cloud registration is a fundamental problem in many domains. Practically, the overlap between point clouds to be registered may be relatively small. Most unsupervised methods lack effective initial evaluation of ov…

Point Cloud Registration

SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks

2024-03-28 · CVPR 2024 1 · Yaxu Xie, Alain Pagani, Didier Stricker

Scene graphs have been recently introduced into 3D spatial understanding as a comprehensive representation of the scene. The alignment between 3D scene graphs is the first step of many downstream tasks such as scene grap…

3D Scene Graph AlignmentGraph MatchingGraph Neural NetworkPoint Cloud Registration+1