D3Former: Jointly Learning Repeatable Dense Detectors and Feature-enhanced Descriptors via Saliency-guided Transformer

• URL: http://arxiv.org/abs/2312.12970v1
• Date: Wed, 20 Dec 2023 12:19:17 GMT
• Title: D3Former: Jointly Learning Repeatable Dense Detectors and Feature-enhanced Descriptors via Saliency-guided Transformer
• Authors: Junjie Gao, Pengfei Wang, Qiujie Dong, Qiong Zeng, Shiqing Xin, Caiming Zhang
• Abstract summary: We introduce a saliency-guided transtextbfformer, referred to as textitD3Former, which entails the joint learning of repeatable textbfDetectors and feature-enhanced textbfDescriptors. Our proposed method consistently outperforms state-of-the-art point cloud matching methods.
• Score: 14.056531181678467
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Establishing accurate and representative matches is a crucial step in addressing the point cloud registration problem. A commonly employed approach involves detecting keypoints with salient geometric features and subsequently mapping these keypoints from one frame of the point cloud to another. However, methods within this category are hampered by the repeatability of the sampled keypoints. In this paper, we introduce a saliency-guided trans\textbf{former}, referred to as \textit{D3Former}, which entails the joint learning of repeatable \textbf{D}ense \textbf{D}etectors and feature-enhanced \textbf{D}escriptors. The model comprises a Feature Enhancement Descriptor Learning (FEDL) module and a Repetitive Keypoints Detector Learning (RKDL) module. The FEDL module utilizes a region attention mechanism to enhance feature distinctiveness, while the RKDL module focuses on detecting repeatable keypoints to enhance matching capabilities. Extensive experimental results on challenging indoor and outdoor benchmarks demonstrate that our proposed method consistently outperforms state-of-the-art point cloud matching methods. Notably, tests on 3DLoMatch, even with a low overlap ratio, show that our method consistently outperforms recently published approaches such as RoReg and RoITr. For instance, with the number of extracted keypoints reduced to 250, the registration recall scores for RoReg, RoITr, and our method are 64.3\%, 73.6\%, and 76.5\%, respectively.

Related papers

• Rethinking Few-shot 3D Point Cloud Semantic Segmentation [62.80639841429669]
  This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS) We focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. To address these issues, we introduce a standardized FS-PCS setting, upon which a new benchmark is built.
  arXiv  Detail & Related papers  (2024-03-01T15:14:47Z)
• Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching [77.97246496316515]
  Open-Vocabulary Keypoint Detection (OVKD) task is innovatively designed to use text prompts for identifying arbitrary keypoints across any species. We have developed a novel framework named Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM) This framework combines vision and language models, creating an interplay between language features and local keypoint visual features.
  arXiv  Detail & Related papers  (2023-10-08T07:42:41Z)
• KDD-LOAM: Jointly Learned Keypoint Detector and Descriptors Assisted LiDAR Odometry and Mapping [9.609585217048664]
  We propose a tightly coupled keypoint detector and descriptor based on a multi-task fully convolutional network with a probabilistic detection loss. Experiments on both indoor and outdoor datasets show that our TCKDD achieves state-of-the-art performance in point cloud registration. We also design a keypoint detector and descriptors-assisted LiDAR odometry and mapping framework (KDD-LOAM), whose real-time odometry relies on keypoint descriptor matching-based RANSAC.
  arXiv  Detail & Related papers  (2023-09-27T04:10:52Z)
• SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data [17.471342278936365]
  We propose a new method to infer keypoints from arbitrary object categories in practical scenarios where point cloud data (PCD) are noisy, down-sampled and arbitrarily rotated. We achieve these desiderata by proposing a new self-supervised training strategy for keypoints estimation. We compare the keypoints estimated by the proposed approach with those of the state-of-the-art unsupervised approaches.
  arXiv  Detail & Related papers  (2023-08-10T08:10:01Z)
• SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection [78.90102636266276]
  We propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA) Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection.
  arXiv  Detail & Related papers  (2022-01-06T08:54:47Z)
• Deep Hough Voting for Robust Global Registration [52.40611370293272]
  We present an efficient framework for pairwise registration of real-world 3D scans, leveraging Hough voting in the 6D transformation parameter space. Our method outperforms state-of-the-art methods on 3DMatch and 3DLoMatch benchmarks while achieving comparable performance on KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-09-09T14:38:06Z)
• UPDesc: Unsupervised Point Descriptor Learning for Robust Registration [54.95201961399334]
  UPDesc is an unsupervised method to learn point descriptors for robust point cloud registration. We show that our learned descriptors yield superior performance over existing unsupervised methods.
  arXiv  Detail & Related papers  (2021-08-05T17:11:08Z)
• Point Cloud Registration using Representative Overlapping Points [10.843159482657303]
  We propose ROPNet, a new deep learning model using Representative Overlapping Points with discriminative features for registration. Specifically, we propose a context-guided module which uses an encoder to extract global features for predicting point overlap score. Experiments over ModelNet40 using noisy and partially overlapping point clouds show that the proposed method outperforms traditional and learning-based methods.
  arXiv  Detail & Related papers  (2021-07-06T12:52:22Z)
• Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression [81.05772887221333]
  We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. We present a simple yet effective approach, named disentangled keypoint regression (DEKR) We empirically show that the proposed direct regression method outperforms keypoint detection and grouping methods.
  arXiv  Detail & Related papers  (2021-04-06T05:54:46Z)
• PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency [38.93610732090426]
  We present PointDSC, a novel deep neural network that explicitly incorporates spatial consistency for pruning outlier correspondences. Our method outperforms the state-of-the-art hand-crafted and learning-based outlier rejection approaches on several real-world datasets.
  arXiv  Detail & Related papers  (2021-03-09T14:56:08Z)
• Unsupervised Learning of 3D Point Set Registration [15.900382629390297]
  Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. This paper proposes Deep-3DAligner, a novel unsupervised registration framework based on a newly introduced deep Spatial Correlation Representation (SCR) feature. Our method starts with optimizing a randomly latent SCR feature, which is then decoded to a geometric transformation to align source and target point sets.
  arXiv  Detail & Related papers  (2020-06-11T05:21:38Z)

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.