Improving performance of deep learning models for 3D point cloud semantic segmentation via attention mechanisms

Aiming at the problem that the relationship between geometric features and semantic features is ignored in the point cloud data downsampling process, which leads to inaccurate segmentation of object boundaries and structural details, this paper proposes a 3D point cloud semantic segmentation network based on multi-scale dense nested type. Firstly, a dense nested network architecture is constructed by nesting multiple multi-scale feature fusion modules to fuse multi-scale features of different directions between encoder-decoder paths, so as to effectively propagate local ge-ometric context information and enhance the ability of cross-scale information interaction. Secondly, a local feature aggregation unit is constructed in the multi-scale feature fusion module, which strengthens the structural awareness within the local point set based on graph convolution and attention mechanism, and promotes the complementarity of local geometric features and abstract semantic information. Then, the cross-layer multi-loss supervision module is combined to further optimize the multi-scale feature propagation, which makes the network training more stable and improves the point cloud segmentation accuracy. Finally, this paper verified the proposed network on the S3DIS dataset. The experimental results show that the proposed network has the mean intersection over Union of 71.2% and the overall accuracy of 88.7%, which is 1.2 and 0.7 percentage points higher than RandLA-Net, respectively, which proves that the proposed network can effectively improve the accuracy of 3D point cloud semantic segmentation.

RGAM: A novel network architecture for 3D point cloud semantic segmentation in indoor scenes

Three-Dimensional (3D) semantic segmentation is an essential building block for interactive Augmented Reality (AR). However, existing Deep Neural Network (DNN) models for segmenting 3D objects are not only computation-intensive but also memory heavy, hindering their deployment on resource-constrained mobile devices. We present the design, implementation and evaluation of Slimmer, a generic and model-independent framework for accelerating 3D semantic segmentation and facilitating its real-time applications on mobile devices. In contrast to the current practice that directly feeds a point cloud to DNN models, Slimmer is motivated by our observation that these models remain high accuracy even if we remove a fraction of points from the input, which can significantly reduce the inference time and memory usage of these models. Our design of Slimmer faces two key challenges. First, the simplification method of point clouds should be lightweight. Otherwise, the reduced inference time may be canceled out by the incurred overhead of input-data simplification. Second, Slimmer still needs to accurately segment the removed points from the input to create a complete segmentation of the original input, again, using a lightweight method. Our extensive performance evaluation demonstrates that, by addressing these two challenges, Slimmer can dramatically reduce the resource utilization of a representative DNN model for 3D semantic segmentation. For example, if we can tolerate 1% accuracy loss, the reduction could be ~20% for inference time and ~9% for memory usage. The reduction increases to around ~27% for inference time and ~15% for memory usage when we can tolerate 2% accuracy loss.

Unsupervised domain adaptation (UDA) is increasingly used for 3D point cloud semantic segmentation tasks due to its ability to address the issue of missing labels for new domains. However, most existing unsupervised domain adaptation methods focus only on uni‐modal data and are rarely applied to multi‐modal data. Therefore, we propose a cross‐modal UDA on multi‐modal datasets that contain 3D point clouds and 2D images for 3D Semantic Segmentation. Specifically, we first propose a Dual discriminator‐based Domain Adaptation (Dd‐bDA) module to enhance the adaptability of different domains. Second, given that the robustness of depth information to domain shifts can provide more details for semantic segmentation, we further employ a Dense depth Feature Fusion (DdFF) module to extract image features with rich depth cues. We evaluate our model in four unsupervised domain adaptation scenarios, i.e., dataset‐to‐dataset (A2D2 → SemanticKITTI), Day‐to‐Night, country‐to‐country (USA → Singapore), and synthetic‐to‐real (VirtualKITTI → SemanticKITTI). In all settings, the experimental results achieve significant improvements and surpass state‐of‐the‐art models.

3D point cloud semantic segmentation has attracted wide attention with its extensive applications in autonomous driving, AR/VR, and robot sensing fields. However, in existing methods, each point in the segmentation results is predicted independently from each other. This property causes the non-contiguity of label sets in three-dimensional space and produces many noisy label points, which hinders the improvement of segmentation accuracy. To address this problem, we first extend adversarial learning to this task and propose a novel framework Attention Adversarial Networks (AttAN). With high-order correlations in label sets learned from the adversarial learning, segmentation network can predict labels closer to the real ones and correct noisy results. Moreover, we design an additive attention block for the segmentation network, which is used to automatically focus on regions critical to the segmentation task by learning the correlation between multi-scale features. Adversarial learning, which explores the underlying relationship between labels in high-dimensional space, opens up a new way in 3D point cloud semantic segmentation. Experimental results on ScanNet and S3DIS datasets show that this framework effectively improves the segmentation quality and outperforms other state-of-the-art methods.

As a pivotal task in 3D scene understanding, 3D point cloud semantic segmentation is often challenged by the presence of mislabeled data in real-world annotations. Such noisy labels can mislead the segmentation model into learning erroneous features during training, thereby degrading its performance. To address this issue, this paper proposes a robust training framework for 3D semantic segmentation based on noisy label correction. The proposed method does not rely on prior knowledge of point cloud density and is capable of learning robust segmentation models under various noise rates. Our approach consists of two core components: a Density-Adaptive Neighborhood Clustering algorithm that dynamically adjusts the neighborhood radius and minimum point count according to local point density variations, and a Dynamically-Weighted Label Refurbishing mechanism, which rectifies noisy labels at the cluster level based on historical prediction confidence. Extensive experiments on the S3DIS dataset demonstrate that our method outperforms existing baselines and state-of-the-art (SOTA) approaches under symmetric, asymmetric, and mixed noise settings. Notably, it maintains strong robustness even under high noise ratios. Furthermore, our method integrates label structures and stores them in a vectorized format, significantly reducing data transfer overhead between CPU and GPU and mitigating resource wastage. This design makes the approach particularly efficient in resource-constrained environments such as cloud servers, where CPU performance is often a bottleneck. As a result, our method achieves a notable improvement in training efficiency, with each training epoch requiring only approximately one-tenth of the time compared to current SOTA methods.

Semantic segmentation of 3D point cloud data is essential for enhanced high-level perception in autonomous platforms. Furthermore, given the increasing deployment of LiDAR sensors onboard of cars and drones, a special emphasis is also placed on non-computationally intensive algorithms that operate on mobile GPUs. Previous efficient state-of-the-art methods relied on 2D spherical projection of point clouds as input for 2D fully convolutional neural networks to balance the accuracy-speed trade-off. This paper introduces a novel approach for 3D point cloud semantic segmentation that exploits multiple projections of the point cloud to mitigate the loss of information inherent in single projection methods. Our Multi-Projection Fusion (MPF) framework analyzes spherical and bird's-eye view projections using two separate highly-efficient 2D fully convolutional models then combines the segmentation results of both views. The proposed framework is validated on the SemanticKITTI dataset where it achieved a mIoU of 55.5 which is higher than state-of-the-art projection-based methods RangeNet++ [23] and PolarNet [44] while being 1.6x faster than the former and 3.1x faster than the latter.

3D point cloud semantic segmentation is a fundamental task for 3D scene understanding. However, most existing pipelines usually use k-NN or ball query operation to form hard neighborhoods, which may cross different semantic objects, resulting low-quality local features. To address this issue, we propose a multi-scale superpoint network that gradually generates multi-scale soft neighborhoods to extract geometric local features, thereby boosting the 3D semantic segmentation performance. Specifically, we present a simple yet efficient superpoint merging module that merge small-scale superpoints to obtain large-scale superpoint by considering the feature similarity of superpoints, so that we can obtain multi-scale geometric features of point clouds. We also develop a superpoint upsampling module that adopt inverse mapping function to propagate multi-scale features from low-resolution point cloud to high-resolution point cloud. By integrating our multi-scale superpoint network into a simple point based semantic segmentation network, our method can obtain SOTA results on S3DIS Area 5 and 6-fold, and competitive results on ScanNet v2.

Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in autonomous driving to allow a vehicle to act safely in its 3D environment. The best performing methods in 3D semantic segmentation or object detection rely on a large amount of annotated data. Yet annotating 3D Lidar data for these tasks is tedious and costly. In this context, we propose a self-supervised pretraining method for 3D perception models that is tailored to autonomous driving data. Specifically, we leverage the availability of synchronized and calibrated image and Lidar sensors in autonomous driving setups for distilling self-supervised pre-trained image representations into 3D models. Hence, our method does not require any point cloud nor image annotations. The keyingredient of our method is the use of superpixels which are used to pool 3D point features and 2D pixel features in visually similar regions. We then train a 3D network on the self-supervised task of matching these pooled point features with the corresponding pooled image pixel features. The advantages of contrasting regions obtained by superpixels are that: (1) grouping together pixels and points of visually coherent regions leads to a more meaningful contrastive task that produces features well adapted to 3D semantic segmentation and 3D object detection; (2) all the different regions have the same weight in the contrastive loss regardless of the number of 3D points sampled in these regions; (3) it mitigates the noise produced by incorrect matching of points and pixels due to occlusions between the different sensors. Extensive experiments on autonomous driving datasets demonstrate the ability of our image-to-Lidar distillation strategy to produce 3D representations that transfer well on semantic segmentation and object detection tasks.

Point cloud has emerged as the most popular three-dimensional (3D) data format in recent years for several scientific and industrial applications. Point cloud semantic segmentation has piqued the researcher’s interest, which is a crucial stage in 3D analysis and scene comprehension. Deep learning-based processing is more feasible to increase the availability of point cloud acquisition tools that is LiDAR systems at the user end. The point cloud learning achieves tremendous success in object detection, object categorization, and semantic segmentation. To summarize the recent works with chronological development, comprehensive review of projection-, voxel-, and direct point-based point cloud semantic segmentation methods is performed from various perspectives. The commonly used point cloud benchmark datasets with their characteristics are discussed, and they are used for the performance analysis and comparison of several state-of-the-art segmentation methods. The quantitative performance analysis of these deep learning models summarizes the trend of semantic segmentation of point clouds. In the context of point cloud semantic segmentation, the various methods have specific roles. Based on the review of methods working and their performance analysis, it is concluded that the projection-based methods prioritize efficiency, which is ideal in unavailability of high-performance computing system. Voxel-based methods capture overall context, serving well in 3D object classification. Point-based approaches excel in fine details and efficiency, suited for tasks like 3D semantic segmentation. Choosing the suitable method depends on the task, data, and resources. KPConv and DGCNN are popular choices, especially for precision and adaptability to point density. However, method performance varies, underlining the need for tailored selection. Hybrid approaches, combining method strengths, promise superior results.

LiDAR has been widely used in autonomous driving systems to provide high-precision 3D geometric information about the vehicle’s surroundings for perception, localization, and path planning. LiDAR-based point cloud semantic segmentation is an important task with a critical real-time requirement. However, most of the existing convolutional neural network (CNN) models for 3D point cloud semantic segmentation are very complex and can hardly be processed at real-time on an embedded platform. In this study, a lightweight CNN structure was proposed for projection-based LiDAR point cloud semantic segmentation with only 1.9 M parameters that gave an 87% reduction comparing to the state-of-the-art networks. When evaluated on a GPU, the processing time was 38.5 ms per frame, and it achieved a 47.9% mIoU score on Semantic-KITTI dataset. In addition, the proposed CNN is targeted on an FPGA using an NVDLA architecture, which results in a 2.74x speedup over the GPU implementation with a 46 times improvement in terms of power efficiency.

In this paper, a Backward Attentive Fusing Network with Local Aggregation Classifier (BAF-LAC) is proposed to improve the performance of 3D point cloud semantic segmentation. It consists of a Backward Attentive Fusing Encoder-Decoder (BAF-ED) to learn semantic features and a Local Aggregation Classifier (LAC) to maintain the context-awareness of points. BAF-ED narrows the semantic gap between the encoder and the decoder via fusing multi-layer encoder features with the decoder features. High-level encoder features are transformed into an attention map to modulate low-level encoder features backward. LAC adaptively enhances the intermediate features in point-wise MLPs via aggregating the features of neighboring points into the center point. It takes the place of commonly used post-processing techniques and retains context consistency into the classifier. Equipped with these modules, BAF-LAC can extract discriminative semantic features and predict smoother results. Extensive experiments on Semantic3D, SemanticKITTI, and S3DIS demonstrate that the proposed method can achieve competitive results against the state-of-the-art methods.

In recent years, the numerous advantages introduced by Building Information modelling (BIM) have led in its application on the heritage environment and giving birth to the concept of H-BIM (Heritage BIM). The resulting demand in heritage survey data processing has focused this research on the development of strategies and methods to improve the construction of three-dimensional and informative models starting from 3D point clouds. The implementation of an automated procedure is fundamental for easing and speeding up the survey data processing and one of the most challenging tasks to achieve this purpose is the problem of semantic segmentation. The research presented in this paper aims at testing already existing methods and exploring new strategies for 3D point cloud semantic segmentation on heritage scenarios focusing on deep learning and neural network techniques.

Semantic segmentation is an important component in understanding the 3D point cloud scene. Whether we can effectively obtain local and global contextual information from points is of great significance in improving the performance of 3D point cloud semantic segmentation. In this paper, we propose a self-attention feature extraction module: the local transformer structure. By stacking the encoder layer composed of this structure, we can extract local features while preserving global connectivity. The structure can automatically learn each point feature from its neighborhoods and is invariant to different point orders. We designed two unique key matrices, each of which focuses on the feature similarities and geometric structure relationships between the points to generate attention weight matrices. Additionally, the cross-skip selection of neighbors is used to obtain larger receptive fields for each point without increasing the number of calculations required, and can therefore better deal with the junction between multiple objects. When the new network was verified on the S3DIS, the mean intersection over union was 69.1%, and the segmentation accuracies on the complex outdoor scene datasets Semantic3D and SemanticKITTI were 94.3% and 87.8%, respectively, which demonstrate the effectiveness of the proposed methods.

The process of segmenting point cloud data into several homogeneous areas with points in the same region having the same attributes is known as 3D segmentation. Segmentation is challenging with point cloud data due to substantial redundancy, fluctuating sample density and lack of apparent organization. The research area has a wide range of robotics applications, including intelligent vehicles, autonomous mapping and navigation. A number of researchers have introduced various methodologies and algorithms. Deep learning has been successfully used to a spectrum of 2D vision domains as a prevailing A.I. methods. However, due to the specific problems of processing point clouds with deep neural networks, deep learning on point clouds is still in its initial stages. This study examines many strategies that have been presented to 3D instance and semantic segmentation and gives a complete assessment of current developments in deep learning-based 3D segmentation. In these approaches’ benefits, draw backs, and design mechanisms are studied and addressed. This study evaluates the impact of various segmentation algorithms on competitiveness on various publicly accessible datasets, as well as the most often used pipelines, their advantages and limits, insightful findings and intriguing future research directions.