In the field of medical image processing, the presence of noise can often result in the obfuscation of crucial details, which in turn can have a detrimental impact on the accuracy of clinical diagnoses. In order to effectively remove noise and improve segmentation performance, this paper proposes a refined Fuzzy C-Means (FCM) algorithm, designated as MKL-FCM. The method commences with Poisson denoising, which enables more effective handling of the noise characteristics inherent to medical images. Subsequently, multi-scale Kullback-Leibler divergence is utilised to analyse local image information across varying scales, facilitating the differentiation between tissues and pathological regions. Furthermore, tight wavelet frames are capable of capturing fine image details, while reverse optimisation of the objective function serves to correct errors in feature reconstruction, thereby enhancing the accuracy of the segmentation process. The experimental results demonstrate that MKL-FCM enhances both image clarity and segmentation accuracy, and outperforms existing methods in terms of efficiency.

Brain tissue segmentation is critical for diagnosing and treating brain diseases, but noise introduced during MRI image acquisition can compromise downstream tasks. To address this, we introduce a Poisson denoising module to eliminate Poisson and mixed noise. However, Poisson denoising may blur local brain tissue details and edges, impacting segmentation accuracy. To overcome this, we propose PDMambaNet, which integrates Poisson denoising, the Mamba architecture, and a Twin-Path Decoder (TPD). One decoder focuses on global detail recovery, while the other restores texture and edge information. This structure minimizes detail loss and improves the model’s ability to capture multi-level features. The collaborative effect of TPD reduces over-smoothing and artifact generation, ensuring the preservation of cross-scale spatial information. Extensive subjective and objective evaluations demonstrate that PDMambaNet outperforms existing methods in segmentation performance. The code is available in the supplementary material.

State Space models (SSMs) like PointMamba provide efficient feature extraction for point cloud self-supervised learning with linear complexity, surpassing Transformers in computational efficiency. However, existing PointMamba-based methods rely on complex token ordering and random masking, disrupting spatial continuity and local semantic correlations. We propose \textbf{ZigzagPointMamba} to address these challenges. The key to our approach is a simple zigzag scan path that globally sequences point cloud tokens, enhancing spatial continuity by preserving the proximity of spatially adjacent point tokens. Yet, random masking impairs local semantic modeling in self-supervised learning. To overcome this, we introduce a Semantic-Siamese Masking Strategy (SMS), which masks semantically similar tokens to facilitate reconstruction by integrating local features of original and similar tokens, thus overcoming dependence on isolated local features and enabling robust global semantic modeling. Our pre-training ZigzagPointMamba weights significantly boost downstream tasks, achieving a 1.59\% mIoU gain on ShapeNetPart for part segmentation, a 0.4\% higher accuracy on ModelNet40 for classification, and 0.19\%, 1.22\%, and 0.72\% higher accuracies respectively for the classification tasks on the OBJ-BG, OBJ-ONLY, and PB-T50-RS subsets of ScanObjectNN. Code is available at https://github.com/Rabbitttttt218/ZigzagPointMamba.

In this paper, we present LiDAR-Net, a new real-scanned indoor point cloud dataset, containing nearly 3.6 billion precisely point-level annotated points, covering an expansive area of 30,000m2. It encompasses three prevalent daily environments, including learning scenes, working scenes, and living scenes. LiDAR-Net is characterized by its non-uniform point distribution, e.g., scanning holes and scanning lines. Additionally, it meticulously records and an-notates scanning anomalies, including reflection noise and ghost. These anomalies stem from specular reflections on glass or metal, as well as distortions due to moving persons. LiDAR-Net's realistic representation of non-uniform distribution and anomalies significantly enhances the training of deep learning models, leading to improved generalization in practical applications. We thoroughly evaluate the performance of state-of-the-art algorithms on LiDAR-Net and provide a detailed analysis of the results. Crucially, our research identifies several fundamental challenges in understanding indoor point clouds, contributing essential insights to future explorations in this field. Our dataset can be found online: http://lidar-net.njumeta.com.

Sparse Subspace Clustering (SSC) is integral to image processing, drawing from spectral clustering foundations. However, prevalent methods, relying on an l1-norm constraint, fail to capture nuanced inter-region correlations, affecting segmentation efficacy. To remedy this, we introduce an Adaptive Gaussian Regularization Constrained SSC for enhanced image segmentation. This method begins with superpixel preprocessing to enrich local information. Given the Gaussian nature of the SSC’s sparse coefficient matrix, a Gaussian probability density function is infused as a regularization term, reinforcing regional image ties and facilitating similarity matrix creation. Using spectral clustering, we then define superpixel clusters leading to the final segmentation. When tested against the BSDS500 and SBD datasets and other leading algorithms, our model showcases marked improvements in natural image segmentation.

Accurate pose estimation over SE(3) is fundamentally crucial for numerous perception tasks, including camera re-localization. While existing learning-based methods estimated from a series of RGB images have significantly improved the accuracy of pose, the majority of models still face one or two limitations. First, few representations on SE(3) are smooth and differential, making them difficult to apply in deep learning frameworks. Second, they often require high computational resources due to complex deep network designs. We in this paper propose the DL-PoseNet to address these issues. Specifically, we present a novel representation for SE(3) which follows the property of smoothness of the pose. We then design a lightweight neural network to regress the pose by developing a differential pose layer. Finally, we introduce a novel loss function and gradient descent method to better supervise the proposed lightweight pose network. Extensive experiments on the camera re-localization task on the Cambridge Landmarks and 7-Scenes datasets demonstrate the superior predictive accuracy and benefits of our method in comparison with the state-of-the-art.

Recently, Spiking Neural Networks (SNNs), enjoying extreme energy efficiency, have drawn much research attention on 2D visual recognition and shown gradually increasing application potential. However, it still remains underexplored whether SNNs can be generalized to 3D recognition. To this end, we present Spiking PointNet in the paper, the first spiking neural model for efficient deep learning on point clouds. We discover that the two huge obstacles limiting the application of SNNs in point clouds are: the intrinsic optimization obstacle of SNNs that impedes the training of a big spiking model with large time steps, and the expensive memory and computation cost of PointNet that makes training a big spiking point model unrealistic. To solve the problems simultaneously, we present a trained-less but learning-more paradigm for Spiking PointNet with theoretical justifications and in-depth experimental analysis. In specific, our Spiking PointNet is trained with only a single time step but can obtain better performance with multiple time steps inference, compared to the one trained directly with multiple time steps. We conduct various experiments on ModelNet10, ModelNet40 to demonstrate the effectiveness of Sipiking PointNet. Notably, our Spiking PointNet even can outperform its ANN counterpart, which is rare in the SNN field thus providing a potential research direction for the following work. Moreover, Spiking PointNet shows impressive speedup and storage saving in the training phase. Our code is open-sourced at https://github.com/DayongRen/Spiking-PointNet.

Abstract Orientation estimation is one of the core problems in several computer vision tasks. Recently deep learning techniques combined with the Bingham distribution have attracted considerable interest towards this problem when considering ambiguities and rotational symmetries of objects. However, existing works suffer from two issues. First, the computational overhead for calculating the normalisation constant of the Bingham distribution is relatively high. Second, the choice of loss functions is uncertain. In light of these problems, we present an online deep Bingham network to estimate the orientation of objects. We sharply reduce the computational overhead of the normalisation constant by directly applying a numerical integration formula. Additionally, we are the first to give theorems on the convexity and Lipschitz continuity of the Bingham distribution's negative log‐likelihood, which formally indicates that it is a proper choice of the loss function. We test our method on three public datasets, namely the UPNA, the T‐LESS and Pascal3D+, showing that our method outperforms the state‐of‐the‐art in terms of orientation accuracy and time efficiency, which can reduce the runtime by more than 6 h compared to the offline methods. The ablation experiments further demonstrate the effectiveness and robustness of our model.