Due to the irregular and disordered data structure in 3D point clouds, prior works have focused on designing more sophisticated local representation methods to capture these complex local patterns. However, the recognition performance has saturated over the past few years, indicating that increasingly complex and redundant designs no longer make improvements to local learning. This phenomenon prompts us to diverge from the trend in 3D vision and instead pursue an alternative and successful solution: deeper neural networks. In this paper, we propose DeepLA-Net, a series of very deep networks for point cloud analysis. The key insight of our approach is to exploit a small but mighty local learning block, which uses 10× fewer FLOPs, enabling the construction of very deep networks. Furthermore, we design a training supervision strategy to ensure smooth gradient backpropagation and optimization in very deep networks. We construct the DeepLA-Net family with a depth of up to 120 blocks — at least 5× deeper than recent methods — trained on a single RTX 3090. An ensemble of the DeepLA-Net achieves state-of-the-art performance on classification and segmentation tasks of S3DIS Area5 (+2.2% mIoU), ScanNet test set (+1.6% mIoU), ScanObjectNN (+2.1% OA), and ShapeNet-Part (+0.9% cls.mIoU). The code are released at https://github.com/zeng-ziyin/DeepLA-Net.

This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios. We observe that the pairwise matching paradigms applied to image set matching often result in ambiguous estimation when the selected independent pairs exhibit significant occlusions or extreme viewpoint changes. This challenge primarily stems from the inherent uncertainty in interpreting intricate 3D structures based on limited two-view observations, as the 3D-to-2D projection leads to significant information loss. To address this, we introduce CoMatcher, a deep multi-view matcher to (i) leverage complementary context cues from different views to form a holistic 3D scene understanding and (ii) utilize cross-view projection consistency to infer a reliable global solution. Building on CoMatcher, we develop a groupwise framework that fully exploits cross-view relationships for large-scale matching tasks. Extensive experiments on various complex scenarios demonstrate the superiority of our method over the mainstream two-view matching paradigm.

Class activation map (CAM) based weakly-supervised semantic segmentation (WSSS) of remote sensing (RS) images has attracted extensive research interests for its potential in reducing annotation cost. However, challenged by unconstrained activation issue, existing methods struggle to delineate object boundaries clearly, making them particularly difficult to separate multiple densely packed objects, which are common in RS images. By conducting an in-depth analysis of RS image characteristics, we observed a strong correlation between object shapes and their semantics. Inspired by this finding, we propose an Intrinsic Shape Activation Network (ISANet) to learn the category-relevant shape priors as geometry constraints for target-focused region activation in WSSS of RS images. The key idea is to distill the intrinsic shape priors from the hybrid features that are deterministic in classification. Specifically, we adopt a dual-branch architecture to decouple the learning of shape and texture features and leverage a shape awareness alignment module to generate boundary-clear CAMs for computing pseudo labels. In this way, CAMs are generated with perception of target shapes, which increases the completeness of activation regions and alleviates the ultrarange responses. Extensive experiments demonstrates the superiority of our method in delineating densely-packed objects with clear contours, which is especially beneficial for separating multiple targets in RS images. Our method improves the mIoU of the state-of-the-art method by 7.9% and 3.3% on the NWPU VHR-10 and iSAID dataset respectively.

Image-level weakly-supervised land-cover classification (WSLC) relies on image labels to free land-cover classification networks from expensive pixel-level annotations. Existing weakly-supervised methods commonly generate class activation maps (CAMs) from a trained classification network to produce pixel-level pseudo labels for training land-cover classification networks. However, CAMs struggle to completely and accurately capture land-covers in remote sensing images due to the lack of precise localization information in weak supervision. To alleviate semantic uncertainty in CAMs, this paper proposes an Expanding-Separating (ES) scheme to generate high-quality CAMs of land-covers. The ES scheme expands activation areas in CAMs by lifting activation values in inactivated regions and suppresses CAM noises by decreasing values in confusing regions. Experimental results on the DeepGlobe dataset demonstrate that the proposed ES scheme significantly improves the quality of CAMs and benefits the training of land-cover classification, achieving state-of-the-art performance.

This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene under-standing. We observe that the search space constructed by current methods for proposal feature grouping and instance point sampling often introduces massive noise to instance detection and mesh reconstruction. Accordingly, we develop AncLearn to generate anchors that dynamically fit instance surfaces to (i) unmix noise and target-related features for offering reliable proposals at the detection stage, and (ii) reduce outliers in object point sampling for directly providing well-structured geometry priors without segmentation during reconstruction. We embed AncLearn into a reconstruction-from-detection learning system (AncRec) to generate high-quality semantic scene models in a purely instance-oriented manner. Experiments conducted on the challenging ScanNetv2 dataset demonstrate that our shape anchor-based method consistently achieves state-of-the-art performance in terms of 3D object detection, layout estimation, and shape reconstruction. The code will be available at https://github.com/Geo-Tell/AncRec.

The wireless capsule endoscope (robot) has become more extensively used due to its comprehensive detection and patient-friendly experience. However, to provide better diagnostic information to medical staff, there is an urgent need for high-accuracy position information of capsule endoscopes during their working inside the human body. In this article, a capsule endoscopy positioning system using a magnetic sensor array is designed. It has two advantages. 1) Most of the existing magnetic positioning method needs to initialize the magnetic moment accurately, which is difficult to meet in practical applications. To solve this issue, this article proposes a method to determine the magnetic moment direction based on an inertial measurement unit. The proposed method can accurately estimate the direction of the magnetic moment even when the roll angle is singular. 2) This article proposes a nonlinear least-squares algorithm for capsule magnetic positioning based on the three-axis magnetometer observation. The algorithm is more robust than the Levenberg–Marquardt (LM) method that is widely used in capsule endoscopy positioning. Furthermore, its computation speed is over 100 times faster than the LM method, which successfully meets the real-time requirements. In this research, a three-axis mechanical platform and a six-axis robot arm are used to build a capsule magnetic positioning evaluation system. Preliminary results show the accuracy (RMS) of the proposed capsule endoscope positioning algorithm was better than 6 mm.

Matching local features between two overlapped images is a fundamental task in photogrammetry and remote sensing. However, images acquired by multiple sensors often differ substantially in properties, thus posing a great challenge to the robustness and flexibility of feature matching methods. In this article, we propose a locally non-linear affine verification (LAV) method for robust multisensor image matching. The main idea of the LAV is the development of a nonlinear regression formulation that practically models the nonlinear deviation of a real surface around a point from its tangent plane during affine verification. Specifically, we start by selecting a restricted set of reliable and well-distributed putative matches as the matching seeds and assign them with neighbors to construct search spaces. In each search space, the regression seeks the smoothest affine model consistent with the latent correct matches, thereby deriving a set of affine parameters to verify correspondence hypotheses for true matches. The verification can be extended to all nearest neighbor matches to discover additional inlier matches. Evaluation on multisensor image datasets with different extents of variations in viewpoint, scale, illumination, and appearance shows that the proposed LAV consistently outperforms existing methods. LAV can achieve a considerable number of high-quality matches, in cases where existing methods provide few or no correct matches.