SGNet: Salient Geometric Network for Point Cloud Registration
- URL: http://arxiv.org/abs/2309.06207v3
- Date: Sat, 20 Jan 2024 15:31:10 GMT
- Title: SGNet: Salient Geometric Network for Point Cloud Registration
- Authors: Qianliang Wu, Yaqing Ding, Lei Luo, Shuo Gu, Chuanwei Zhou, Jin Xie,
Jian Yang
- Abstract summary: Point Cloud Registration (PCR) is a critical and challenging task in computer vision.
Previous methods have encountered challenges with ambiguous matching due to similarity among patch blocks.
We propose a new framework that includes several novel techniques.
- Score: 34.817412933906525
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point Cloud Registration (PCR) is a critical and challenging task in computer
vision. One of the primary difficulties in PCR is identifying salient and
meaningful points that exhibit consistent semantic and geometric properties
across different scans. Previous methods have encountered challenges with
ambiguous matching due to the similarity among patch blocks throughout the
entire point cloud and the lack of consideration for efficient global geometric
consistency. To address these issues, we propose a new framework that includes
several novel techniques. Firstly, we introduce a semantic-aware geometric
encoder that combines object-level and patch-level semantic information. This
encoder significantly improves registration recall by reducing ambiguity in
patch-level superpoint matching. Additionally, we incorporate a prior knowledge
approach that utilizes an intrinsic shape signature to identify salient points.
This enables us to extract the most salient super points and meaningful dense
points in the scene. Secondly, we introduce an innovative transformer that
encodes High-Order (HO) geometric features. These features are crucial for
identifying salient points within initial overlap regions while considering
global high-order geometric consistency. To optimize this high-order
transformer further, we introduce an anchor node selection strategy. By
encoding inter-frame triangle or polyhedron consistency features based on these
anchor nodes, we can effectively learn high-order geometric features of salient
super points. These high-order features are then propagated to dense points and
utilized by a Sinkhorn matching module to identify key correspondences for
successful registration. In our experiments conducted on well-known datasets
such as 3DMatch/3DLoMatch and KITTI, our approach has shown promising results,
highlighting the effectiveness of our novel method.
Related papers
- Mesh Denoising Transformer [104.5404564075393]
Mesh denoising is aimed at removing noise from input meshes while preserving their feature structures.
SurfaceFormer is a pioneering Transformer-based mesh denoising framework.
New representation known as Local Surface Descriptor captures local geometric intricacies.
Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation.
arXiv Detail & Related papers (2024-05-10T15:27:43Z) - GeoTransformer: Fast and Robust Point Cloud Registration with Geometric
Transformer [63.85771838683657]
We study the problem of extracting accurate correspondences for point cloud registration.
Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints.
We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching.
arXiv Detail & Related papers (2023-07-25T02:36:04Z) - Improving RGB-D Point Cloud Registration by Learning Multi-scale Local
Linear Transformation [38.64501645574878]
Point cloud registration aims at estimating the geometric transformation between two point cloud scans.
Recent point cloud registration methods have tried to apply RGB-D data to achieve more accurate correspondence.
We propose a new Geometry-Aware Visual Feature Extractor (GAVE) that employs multi-scale local linear transformation.
arXiv Detail & Related papers (2022-08-31T14:36:09Z) - GeoSegNet: Point Cloud Semantic Segmentation via Geometric
Encoder-Decoder Modeling [39.35429984469557]
We present a robust semantic segmentation network dubbed GeoSegNet.
Our GeoSegNet consists of a multi-geometry based encoder and a boundary-guided decoder.
Experiments show obvious improvements of our method over its competitors in terms of the overall segmentation accuracy and object boundary clearness.
arXiv Detail & Related papers (2022-07-14T09:24:05Z) - Geometric Transformer for Fast and Robust Point Cloud Registration [53.10568889775553]
We study the problem of extracting accurate correspondences for point cloud registration.
Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult in low-overlap scenarios.
We propose Geometric Transformer to learn geometric feature for robust superpoint matching.
arXiv Detail & Related papers (2022-02-14T13:26:09Z) - Neighborhood-aware Geometric Encoding Network for Point Cloud
Registration [0.0]
Neighborhood-aware Geometric.
Network (NgeNet) for accurate point cloud registration.
NgeNet is model-agnostic, which could be easily migrated to other networks.
arXiv Detail & Related papers (2022-01-28T13:04:54Z) - Robust Partial-to-Partial Point Cloud Registration in a Full Range [12.86951061306046]
We propose Graph Matching Consensus Network (GMCNet), which estimates pose-invariant correspondences for fullrange 1 Partial-to-Partial point cloud Registration (PPR)
GMCNet encodes point descriptors for each point cloud individually without using crosscontextual information, or ground truth correspondences for training.
arXiv Detail & Related papers (2021-11-30T17:56:24Z) - PCAM: Product of Cross-Attention Matrices for Rigid Registration of
Point Clouds [79.99653758293277]
PCAM is a neural network whose key element is a pointwise product of cross-attention matrices.
We show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets.
arXiv Detail & Related papers (2021-10-04T09:23:27Z) - DeepI2P: Image-to-Point Cloud Registration via Deep Classification [71.3121124994105]
DeepI2P is a novel approach for cross-modality registration between an image and a point cloud.
Our method estimates the relative rigid transformation between the coordinate frames of the camera and Lidar.
We circumvent the difficulty by converting the registration problem into a classification and inverse camera projection optimization problem.
arXiv Detail & Related papers (2021-04-08T04:27:32Z) - Self-supervised Geometric Perception [96.89966337518854]
Self-supervised geometric perception is a framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels.
We show that SGP achieves state-of-the-art performance that is on-par or superior to the supervised oracles trained using ground-truth labels.
arXiv Detail & Related papers (2021-03-04T15:34:43Z)
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.