PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing

By Hengshuang Zhao, Li Jiang, Chi-Wing Fu, Jiaya Jia. Computer Vision and Pattern Recognition, 2019

821 citations recorded by the source corpus.

This paper presents PointWeb, a new approach to extract contextual features from local neighborhood in a point cloud. Unlike previous work, we densely connect each point with every other in a local neighborhood, aiming to specify feature of each point based on the local region characteristics for better representing the region. A novel module, namely Adaptive Feature Adjustment (AFA) module, is presented to find the interaction between points. For each local region, an impact map carrying element-wise impact between point pairs is applied to the feature difference map. Each feature is then pulled or pushed by other features in the same region according to the adaptively learned impact indicators. The adjusted features are well encoded with region information, and thus benefit the point cloud recognition tasks, such as point cloud segmentation and classification. Experimental results show that our model outperforms the state-of-the-arts on both semantic segmentation and shape classification datasets.

Subfields: Computational Mechanics, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/3d7df210adf70f30f952739553201994b92e5630

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Environmental Engineering

In Geology

Citations in the corpus

PU-GAN: A Point Cloud Upsampling Adversarial Network (2019, background): “, PointNet [23], PointNet++ [24], SpiderCNN [35], KCNet [26], SPLATNet [29], PointCNN [20], PointConv [13], PointWeb [44], DGCNN [31], etc.”
PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling (2020, methodology): “The underlying reason is that, currently, most appealing methods for feature learning is to query a local group around the each sampled point, and then they construct the graph-based learning [30, 42, 50, 14] or define convolution-like operations [12, 47, 8, 3, 44, 34] (we denote them as Point Local”
PCT: Point cloud transformer (2020, neutral): “nts Accuracy PointNet [21] P 1k 89.2% SO-Net [16] P, N 2k 90.9% Kd-Net [11] P 32k 91.8% PointNet++ [22] P 1k 90.7% PointNet++ [22] P, N 5k 91.9% PointGrid [14] P 1k 92.0% PCNN [1] P 1k 92.3% PointWeb [38] P 1k 92.3% PointCNN [17] P 1k 92.5% PointConv [31] P, N 1k 92.5% A-CNN [12] P, N 1k 92.6% P2Seq”
Stratified Transformer for 3D Point Cloud Segmentation (2022, methodology): “Abundant methods [7, 15, 16, 34, 35, 41, 52, 61, 62] have explored 3D point cloud segmentation and obtained decent performance.”
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation (2020, background): “Other approaches [51, 48, 57, 52, 21] enhance feature learning on local regions by dynamic context aggregation and attention modules.”
Point Transformer V2: Grouped Vector Attention and Partition-based Pooling (2022, methodology): “Point-based methods extract features directly from the point cloud rather than projecting or quantizing irregular point clouds onto regular grids in 2D or 3D [19, 4, 20, 5].”
Point Transformer V3: Simpler, Faster, Stronger (2023, background): “Point-based methods, by contrast, process point clouds directly [52, 62, 63, 77, 105] and have recently seen a shift towards transformer-based architectures [27, 65, 90, 101, 106].”
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (2019, methodology): “This result clearly demonstrates that most existing networks [44, 33, 60, 36, 70, 66] are only able to be optimized on small blocks of point clouds primarily because they rely on the expensive sampling approaches.”
An End-to-End Transformer Model for 3D Object Detection (2021, methodology): “Following prior work [90], we report two metrics to evaluate shape classi-ﬁcation performance: 1) Overall Accuracy (OA) evaluates how many point clouds we classify correctly; and 2) Class-Mean Accuracy (mAcc) evaluates the accuracy for each class independently, followed by an average over the…”
Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis (2021, methodology): “Following them, recent works have extended the point-wise method to various directions, which include designing advanced convolution operations [12, 43, 38, 20], considering a wider neighborhood [15, 50, 36, 22], and the adaptive aggregation of it [6, 44, 49, 45].”
From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network (2019, methodology): “Instead of using point-based methods like [27], [28], [57], [58], [59], [60], [61] for extracting point-wise features from the point cloud, as show in the left part of Fig.”
Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene (2020, background): “ural models come to widely-studied in point cloud segmentation field since it can directly process the point cloud. Categories of pointbased deep learning models mainly include feature pooling models [15, 23, 24, 43], convolution-based models [20, 30, 34], graph-based models [18, 33, 37] and attenti”
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection (2019, background): “Representation learning on point clouds has drawn lots of attention on improving the performance of point cloud classification and segmentation [25, 26, 45, 34, 7, 42, 16, 30, 36, 8, 32, 10, 21, 3].”