RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registration
- URL: http://arxiv.org/abs/2405.07594v1
- Date: Mon, 13 May 2024 09:56:28 GMT
- Title: RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registration
- Authors: Congjia Chen, Xiaoyu Jia, Yanhong Zheng, Yufu Qu,
- Abstract summary: We propose a new feature combination framework, which applies a looser but more effective fusion and can achieve better performance.
Experiments on ScanNet show that our method achieves a state-of-the-art performance and the rotation accuracy of 99.1%.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point cloud registration is a fundamental task for estimating rigid transformations between point clouds. Previous studies have used geometric information for extracting features, matching and estimating transformation. Recently, owing to the advancement of RGB-D sensors, researchers have attempted to utilize visual information to improve registration performance. However, these studies focused on extracting distinctive features by deep feature fusion, which cannot effectively solve the negative effects of each feature's weakness, and cannot sufficiently leverage the valid information. In this paper, we propose a new feature combination framework, which applies a looser but more effective fusion and can achieve better performance. An explicit filter based on transformation consistency is designed for the combination framework, which can overcome each feature's weakness. And an adaptive threshold determined by the error distribution is proposed to extract more valid information from the two types of features. Owing to the distinctive design, our proposed framework can estimate more accurate correspondences and is applicable to both hand-crafted and learning-based feature descriptors. Experiments on ScanNet show that our method achieves a state-of-the-art performance and the rotation accuracy of 99.1%.
Related papers
- SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised
Learning for Robust Infrared Small Target Detection [53.19618419772467]
Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds.
With the development of Transformer, the scale of SIRST models is constantly increasing.
With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
arXiv Detail & Related papers (2024-03-08T16:14:54Z) - Enhancing Deformable Local Features by Jointly Learning to Detect and
Describe Keypoints [8.390939268280235]
Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval.
We propose DALF, a novel deformation-aware network for jointly detecting and describing keypoints.
Our approach also enhances the performance of two real-world applications: deformable object retrieval and non-rigid 3D surface registration.
arXiv Detail & Related papers (2023-04-02T18:01:51Z) - 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) - Learning Dense Features for Point Cloud Registration Using Graph
Attention Network [0.0]
We introduce a framework that efficiently and economically extracts dense features using graph attention network for point cloud matching and registration.
The detector of the DFGAT is responsible for finding highly reliable key points in large raw data sets.
The graph attention network uses the attention mechanism that enriches the relationships between point clouds.
arXiv Detail & Related papers (2022-06-14T10:28:57Z) - Enabling Efficient Deep Convolutional Neural Network-based Sensor Fusion
for Autonomous Driving [10.326217500172689]
Fusion between DCNNs has been proved as a promising strategy to achieve satisfactory perception accuracy.
We propose a feature disparity metric to measure the degree of feature disparity between the feature maps being fused.
We also propose a Layer-sharing technique in the deep layer that can achieve better accuracy with less computational overhead.
arXiv Detail & Related papers (2022-02-22T23:35:30Z) - Compactness Score: A Fast Filter Method for Unsupervised Feature
Selection [66.84571085643928]
We propose a fast unsupervised feature selection method, named as, Compactness Score (CSUFS) to select desired features.
Our proposed algorithm seems to be more accurate and efficient compared with existing algorithms.
arXiv Detail & Related papers (2022-01-31T13:01:37Z) - ACFNet: Adaptively-Cooperative Fusion Network for RGB-D Salient Object
Detection [0.0]
We propose an adaptively-cooperative fusion network (ACFNet) with ResinRes structure for salient object detection.
For different objects, the features generated by different types of convolution are enhanced or suppressed by the gated mechanism for segmentation optimization.
Sufficient experiments conducted on RGB-D SOD datasets illustrate that the proposed network performs favorably against 18 state-of-the-art algorithms.
arXiv Detail & Related papers (2021-09-10T02:34:27Z) - GhostSR: Learning Ghost Features for Efficient Image Super-Resolution [49.393251361038025]
Single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs.
We propose to use shift operation to generate the redundant features (i.e., Ghost features) of SISR models.
We show that both the non-compact and lightweight SISR models embedded in our proposed module can achieve comparable performance to that of their baselines.
arXiv Detail & Related papers (2021-01-21T10:09:47Z) - Progressively Guided Alternate Refinement Network for RGB-D Salient
Object Detection [63.18846475183332]
We aim to develop an efficient and compact deep network for RGB-D salient object detection.
We propose a progressively guided alternate refinement network to refine it.
Our model outperforms existing state-of-the-art approaches by a large margin.
arXiv Detail & Related papers (2020-08-17T02:55:06Z) - Bi-directional Cross-Modality Feature Propagation with
Separation-and-Aggregation Gate for RGB-D Semantic Segmentation [59.94819184452694]
Depth information has proven to be a useful cue in the semantic segmentation of RGBD images for providing a geometric counterpart to the RGB representation.
Most existing works simply assume that depth measurements are accurate and well-aligned with the RGB pixels and models the problem as a cross-modal feature fusion.
In this paper, we propose a unified and efficient Crossmodality Guided to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively.
arXiv Detail & Related papers (2020-07-17T18:35:24Z) - Hierarchical Dynamic Filtering Network for RGB-D Salient Object
Detection [91.43066633305662]
The main purpose of RGB-D salient object detection (SOD) is how to better integrate and utilize cross-modal fusion information.
In this paper, we explore these issues from a new perspective.
We implement a kind of more flexible and efficient multi-scale cross-modal feature processing.
arXiv Detail & Related papers (2020-07-13T07:59:55Z)
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.