The lightweight model for salient object detection in optical remote sensing images (SOD-RSI) is a recent emerging topic. Due to the complexity of the task, recently published works have achieved effective model compression but have not yet achieved the desired detection speed. To truly release the detection speed of lightweight models while ensuring a favorable accuracy-efficiency tradeoff, we propose a new speed-oriented lightweight SOD-RSI network (SOLNet), which has significant advantages in detection speed. Specifically, we design a lightweight group attention (LGA) module to deconstruct–interact–recombine channel features and an enhanced dynamic encoding (EDE) module for dynamically capturing spatial information. On this basis, the dynamically enhanced aggregation module (DEAM) is further proposed, which mines the intrinsic correlation of feature information by decoding high-level feature maps, eliminating the need to pay additional attention to other scales. SOLNet completes lightweight and efficient decoding through simple cascade aggregation operations. Notably, we also propose an evaluation strategy that takes both speed and accuracy into account, extending a novel lightweight gain (Lg) metric for SOD-RSI. This not only effectively reveals the under-gain issue of lightweight models but also provides theoretical support for the evaluation of subsequent lightweight works. Experimental results on the challenging EORSSD and ORSSD datasets show that SOLNet achieves significant speed improvements and is the state-of-the-art (SOTA) lightweight SOD-RSI method. The code is available at https://github.com/SpiritAshes/SOLNet .

Point feature-based visual simultaneous localization and mapping (SLAM) systems are prone to performance degradation in low-texture environments due to insufficient extraction of point features. In this paper, we propose a tightly-coupled stereo visual-inertial SLAM system with point and line features (PLI-SLAM) to enhance the robustness and reliability of systems in low-texture environments. We improve Edge Drawing lines (EDlines) for line feature detection by introducing curvature detection and a new standard for minimum line segment length to improve the accuracy of the line features, while reducing the line feature detection time. We contribute also with an improved adapting factor based on experiment to adjust the error weight of line features, which further improves the localization accuracy of the system. Our system has been tested on the EuRoC dataset. Tests on public datasets and in real environments have shown that PLI-SLAM achieves high accuracy. Furthermore, PLI-SLAM could still operate robustly even in some challenging environments. The processing time of our method is reduced by 28%, compared to the ORB-LINE-SLAM based on point and line, when using Line Segment Detector (LSD).

In view of the poor performance of traditional feature point detection methods in low-texture situations, we design a new self-supervised feature extraction network that can be applied to the visual odometer (VO) front-end feature extraction module based on the deep learning method. First, the network uses the feature pyramid structure to perform multi-scale feature fusion to obtain a feature map containing multi-scale information. Then, the feature map is passed through the position attention module and the channel attention module to obtain the feature dependency relationship of the spatial dimension and the channel dimension, respectively, and the weighted spatial feature map and the channel feature map are added element by element to enhance the feature representation. Finally, the weighted feature maps are trained for detectors and descriptors respectively. In addition, in order to improve the prediction accuracy of feature point locations and speed up the network convergence, we add a confidence loss term and a tolerance loss term to the loss functions of the detector and descriptor, respectively. The experiments show that our network achieves satisfactory performance under the Hpatches dataset and KITTI dataset, indicating the reliability of the network.

Three-dimensional object detection from LiDAR point clouds is essential for autonomous driving, yet existing methods typically rely on costly and extensively annotated datasets. Self-supervised masked autoencoders (MAE) provide a promising alternative, but effectively capturing local geometric structures while maintaining computational efficiency remains challenging. This paper presents DS-MAE, a depthwise separable masked autoencoder for self-supervised 3D point cloud detection. DS-MAE introduces a pyramidal transformer encoder with depthwise separable attention to enhance local geometric feature extraction while reducing computational cost. A depthwise separable generative decoder is further designed for multi-scale masked feature reconstruction, while a density-aware reconstruction loss accounts for the non-uniform point density of LiDAR observations. Experiments on the KITTI, Waymo Open Dataset (WOD), and a small-scale subset of the ONCE dataset demonstrate the effectiveness of DS-MAE, achieving 67.95%, 67.70%, and 58.92% mAP, respectively. On WOD, the reported performance is achieved using only 20% of the labeled training data, demonstrating the effectiveness of DS-MAE under limited supervision.

With the increasing popularity of autonomous driving and 3D reconstruction, keypoint detection, as a key link in visual localization, has become a hot topic in current research. However, existing keypoint detection methods rarely pay attention to the difficulty differences of samples and lack a progressive learning mechanism, which often leads to overfitting for simple samples and underfitting for complex samples, limiting the overall performance of the model. To address these issues, we propose a novel progressive gradient-guided self-distillation method (PG² SD) for keypoint detection, which possesses self-evolutionary learning capabilities. Specifically, we propose a progressive gradient constraint strategy (PGCS) that dynamically adjusts the gradient contributions of different samples, enabling the model to adapt to the evolving learning capability during training. On this basis, we propose a gradient-guided self-distillation strategy (G² SDS), which integrates seamlessly with PGCS to alleviate the insufficient feature representation of hard samples in the early training stage. We further design a novel loss function to achieve dynamic collaboration between PGCS and G² SDS, allowing G² SDS to adaptively adjust the self-distillation parameters through the PGCS. Experimental results on multiple benchmark datasets show that our method achieves state-of-theart performance on image matching, visual localization, and 3D reconstruction tasks without designing a proprietary network, indicating broad application prospects.