ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models

• URL: http://arxiv.org/abs/2312.03032v3
• Date: Sun, 15 Dec 2024 09:59:44 GMT
• Title: ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models
• Authors: Weijie Wang, Wenqi Ren, Guofeng Mei, Bin Ren, Xiaoshui Huang, Fabio Poiesi, Nicu Sebe, Bruno Lepri,
• Abstract summary: State-of-the-art 3D point cloud registration methods rely on labeled 3D datasets for training.<n>We introduce ZeroReg, a zero-shot registration approach that utilizes 2D foundation models to predict 3D correspondences.
• Score: 77.84408427496025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: State-of-the-art 3D point cloud registration methods rely on labeled 3D datasets for training, which limits their practical applications in real-world scenarios and often hinders generalization to unseen scenes. Leveraging the zero-shot capabilities of foundation models offers a promising solution to these challenges. In this paper, we introduce ZeroReg, a zero-shot registration approach that utilizes 2D foundation models to predict 3D correspondences. Specifically, ZeroReg adopts an object-to-point matching strategy, starting with object localization and semantic feature extraction from multi-view images using foundation models. In the object matching stage, semantic features help identify correspondences between objects across views. However, relying solely on semantic features can lead to ambiguity, especially in scenes with multiple instances of the same category. To address this, we construct scene graphs to capture spatial relationships among objects and apply a graph matching algorithm to these graphs to accurately identify matched objects. Finally, computing fine-grained point-level correspondences within matched object regions using algorithms like SuperGlue and LoFTR achieves robust point cloud registration. Evaluations on benchmarks such as 3DMatch, 3DLoMatch, and ScanNet demonstrate ZeroReg's competitive performance, highlighting its potential to advance point-cloud registration by integrating semantic features from foundation models.

Related papers

• Open-Vocabulary Octree-Graph for 3D Scene Understanding [54.11828083068082]
  Octree-Graph is a novel scene representation for open-vocabulary 3D scene understanding. An adaptive-octree structure is developed that stores semantics and depicts the occupancy of an object adjustably according to its shape.
  arXiv  Detail & Related papers  (2024-11-25T10:14:10Z)
• 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration [45.579241614565376]
  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.
  arXiv  Detail & Related papers  (2024-11-12T12:04:44Z)
• PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training [90.06520673092702]
  We present PointRegGPT, boosting 3D point cloud registration using generative point-cloud pairs for training. To our knowledge, this is the first generative approach that explores realistic data generation for indoor point cloud registration.
  arXiv  Detail & Related papers  (2024-07-19T06:29:57Z)
• Zero-shot Point Cloud Completion Via 2D Priors [52.72867922938023]
  3D point cloud completion is designed to recover complete shapes from partially observed point clouds. We propose a zero-shot framework aimed at completing partially observed point clouds across any unseen categories.
  arXiv  Detail & Related papers  (2024-04-10T08:02:17Z)
• SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks [14.548198408544032]
  We treat 3D scene graph alignment as a partial graph-matching problem and propose to solve it with a graph neural network. We reuse the geometric features learned by a point cloud registration method and associate the clustered point-level geometric features with the node-level semantic feature. We propose a point-matching rescoring method, that uses the node-wise alignment of the 3D scene graph to reweight the matching candidates from a pre-trained point cloud registration method.
  arXiv  Detail & Related papers  (2024-03-28T15:01:58Z)
• SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registration [5.641476052216014]
  We introduce SphereNet to learn a noise-robust and unseen-general descriptor for point cloud registration. A new benchmark 3DMatch-noise with strong noise is introduced to evaluate our methods. It sets a new state-of-the-art performance for the 3DMatch and 3DLoMatch benchmarks with 93.5% and 75.6% registration recall.
  arXiv  Detail & Related papers  (2023-07-18T15:37:35Z)
• 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)
• Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version) [13.286247750893681]
  3D point cloud registration is a fundamental problem in computer vision and robotics. We propose a novel deep graph matching-based framework for point cloud registration.
  arXiv  Detail & Related papers  (2022-11-09T06:05:25Z)
• ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs [14.377604289952188]
  Low-overlap regions between paired point clouds make the captured features very low-confidence. We propose a misaligned image supported registration network for low-overlap point cloud pairs, dubbed ImLoveNet.
  arXiv  Detail & Related papers  (2022-07-02T13:17:34Z)
• REGTR: End-to-end Point Cloud Correspondences with Transformers [79.52112840465558]
  We conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC. We propose an end-to-end framework to directly predict the final set of correspondences. Our approach achieves state-of-the-art performance on 3DMatch and ModelNet benchmarks.
  arXiv  Detail & Related papers  (2022-03-28T06:01:00Z)
• 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)
• 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)
• OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration [31.108056345511976]
  OMNet is a global feature based iterative network for partial-to-partial point cloud registration. We learn masks in a coarse-to-fine manner to reject non-overlapping regions, which converting the partial-to-partial registration to the registration of the same shapes.
  arXiv  Detail & Related papers  (2021-03-01T11:59:59Z)
• 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)
• ParaNet: Deep Regular Representation for 3D Point Clouds [62.81379889095186]
  ParaNet is a novel end-to-end deep learning framework for representing 3D point clouds. It converts an irregular 3D point cloud into a regular 2D color image, named point geometry image (PGI) In contrast to conventional regular representation modalities based on multi-view projection and voxelization, the proposed representation is differentiable and reversible.
  arXiv  Detail & Related papers  (2020-12-05T13:19:55Z)
• End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences [17.70819292121181]
  3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds. In this paper, we present an end-to-end deep-learning based approach to resolve the point cloud registration problem.
  arXiv  Detail & Related papers  (2020-11-30T06:55:05Z)
• Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration [80.69255347486693]
  We introduce a GRAPH-Induced feaTure Extraction pipeline, a simple yet powerful feature and keypoint detector. We construct a generic graph-based learning scheme to describe point cloud regions and extract salient points. We Reformulate the 3D keypoint pipeline with graph neural networks which allow efficient processing of the point set.
  arXiv  Detail & Related papers  (2020-10-18T19:41:09Z)

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.