Recently, color point cloud registration has begun to receive attention. Unlike geometric-only point clouds, color point clouds incorporate additional color information. Therefore, color point cloud registration can achieve higher accuracy than geometric-only point cloud registration. Despite the success, existing methods are computationally intensive due to the high resource demands of Transformer. In this paper, we propose a Mamba architecture based registration algorithm, CGFMamba-PCR, with color-geometric fusion. Specifically, we propose CGFMamba, a novel color-geometric fusion Mamba network for color point cloud registration, which enhances feature representation through color-geometric guided point ordering and positional encoding. For the input color point cloud pair, they are passed through CGFMamba based feature extraction module to obtain their corresponding features. Then, these features are passed through feature matching and outlier rejection modules to obtain final registration result. Furthermore, an ordering method for the Mamba architecture is proposed that clusters color hue and sorts spatial coordinates. Experiments on Color3DMatch and Color3DLoMatch datasets demonstrate that the proposed algorithm outperforms the state-of-the-art (SOTA) methods. The code of the proposed algorithm will be open-sourced upon acceptance of this paper.

This study proposed a lumped modeling approach for quantum-well (QW) semiconductor optical amplifiers (SOAs), focusing on simulating their nonlinear dynamics to accurately reflect real-world device behavior. QW-SOAs are widely adopted in optical communication systems due to their superior performance compared to bulk and high reliability compared to quantum dot SOAs. However, traditional simulation methods, such as traveling-wave (TW) models, require computationally intensive two-dimensional (time and space) analyses, resulting in prohibitively long simulation time. To address this challenge, we propose a novel lumped model that reduces the simulation dimensionality from two to one as compared to the distributed TW model. This approach significantly enhances computational efficiency, achieving simulation speed improvements of tens to thousands of times while maintaining strong consistency with TW model results.

Prohibited item detection based on X-ray images is one of the most effective security inspection methods. However, the foreground-background feature coupling caused by the overlapping phenomenon specific to X-ray images makes general detectors designed for natural images perform poorly. To address this issue, we propose a Category Semantic Prior Contrastive Learning (CSPCL) mechanism, which aligns the class prototypes perceived by the classifier with the content queries to correct and supplement the missing semantic information responsible for classification, thereby enhancing the model sensitivity to foreground features. To achieve this alignment, we design a specific contrastive loss, CSP loss, which comprises the Intra-Class Truncated Attraction (ITA) loss and the Inter-Class Adaptive Repulsion (IAR) loss, and outperforms classic contrastive losses. Specifically, the ITA loss leverages class prototypes to attract intra-class content queries and preserves essential intra-class diversity via a gradient truncation function. The IAR loss employs class prototypes to adaptively repel inter-class content queries, with the repulsion strength scaled by prototype-prototype similarity, thereby improving inter-class discriminability, especially among similar categories. CSPCL is general and can be easily integrated into Deformable DETR-based models. Extensive experiments on the PIXray, OPIXray, PIDray, and CLCXray datasets demonstrate that CSPCL significantly enhances the performance of various state-of-the-art models without increasing inference complexity. The code is publicly available at https://github.com/Limingyuan001/CSPCL.

In recent years, the local feature-based point cloud registration methods have attracted more attention for their high robustness. The state-of-the-art local feature-based pipeline consists of local feature extraction, feature matching, and outlier rejection. However, the accuracy of this pipeline decreases significantly between low-overlap point clouds. In this article, we propose a novel hand-crafted framework to realize efficient low-overlap point cloud registration through point cloud partitioning, semiglobal point cloud block matching, and best transformation selection with refinement. Experimental results on benchmark datasets show that the proposed algorithm presents the superior performance over the previous methods on low-overlap scenes under different features and achieves very competitive accuracy on non-low-overlap data.

Point cloud registration plays an important role in many applications of computer vision and robotics. Outlier rejection is an essential step in this task. In this letter, we propose an efficient hand-crafted outlier rejection algorithm for point cloud registration. The proposed method includes four modules: seed selection, consensus set construction and sampling, transformation matrix calculation, and hypothesis selection. Particularly, we propose a novel seed selection module based on the addition of elements in the Spatial Consistency (SC) matrix and a new noise suppression strategy in constructing consensus sets. Experimental results on various datasets show that the proposed algorithm presents superior performance over the previous hand-crafted methods.

In recent years, the feature-based point cloud registration methods have attracted more attention. However, most existing methods focus on extracting features with strong antiinterference ability from a single point cloud while neglecting the differences within point cloud pairs. In this paper, unlike these methods treating each point cloud independently, we instead consider the information between point cloud pairs when extracting features. Specifically, we propose a cross-attention-based network for modeling the correlation between a pair of point clouds, where a 3D cross-attention mechanism is proposed and combined with 3D convolution elegantly for feature extraction. The extracted features achieve better robustness under various conditions, such as rotation and translation changes. Then accurate point cloud registration is achieved by matching these features. Experimental results on 3DMatch dataset show that the proposed method achieves state-of-the-art performance on feature matching and point cloud registration tasks compared with the previous feature-based methods.

Today, there are an increasing number of Unmanned Aerial Vehicle (UAV) platforms being equipped with video for real-time observation. Unmanned Aerial Vehicle Systems (UAVs) have been generally used in a great variety of missions because of its inexpensiveness and flexibility. However, UAV often experience unintended translation and rotation due to atmospheric turbulence. And it leads the compensation image to losing lots of information when the large drift occurs. In order to get rid of the unwanted jitter and retain the most information, an estimate of the intentional motion is necessary. This paper presents a novel approach to estimating the intentional motion by adaptive compensation algorithm. And it can retain image information and remove image jitter when the pre-path is deemed to be a straight line. The method has been demonstrated through a series of experiments on real aviation video data.