PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling

By Xu Yan, Chaoda Zheng, Zhuguo Li, Sheng Wang, Shuguang Cui. Computer Vision and Pattern Recognition, 2020

671 citations recorded by the source corpus.

Raw point clouds data inevitably contains outliers or noise through acquisition from 3D sensors or reconstruction algorithms. In this paper, we present a novel end-to-end network for robust point clouds processing, named PointASNL, which can deal with point clouds with noise effectively. The key component in our approach is the adaptive sampling (AS) module. It first re-weights the neighbors around the initial sampled points from farthest point sampling (FPS), and then adaptively adjusts the sampled points beyond the entire point cloud. Our AS module can not only benefit the feature learning of point clouds, but also ease the biased effect of outliers. To further capture the neighbor and long-range dependencies of the sampled point, we proposed a local-nonlocal (L-NL) module inspired by the nonlocal operation. Such L-NL module enables the learning process insensitive to noise. Extensive experiments verify the robustness and superiority of our approach in point clouds processing tasks regardless of synthesis data, indoor data, and outdoor data with or without noise. Specifically, PointASNL achieves state-of-the-art robust performance for classification and segmentation tasks on all datasets, and significantly outperforms previous methods on real-world outdoor SemanticKITTI dataset with considerate noise.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/40b36071bd553b9fda2ea26c6d4e057f37c0e7e7

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 Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (2022, background): “Later on, many studies design point-wise MLP [25,26], adaptive weight [27, 28] and pseudo grid [29, 30] based methods to extract lo-cal features of point clouds or exploit nonlocal operators [31–33] to learn long distance dependency.”
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation (2020, background): “Mainstream methods [25, 31, 39, 36, 32, 20, 10, 45, 41, 33, 24, 26] of indoor point cloud segmentation learn the point features based on the raw point directly, which are often based on the pioneering work, i.”
Self-Supervised Pretraining of 3D Features on any Point-Cloud (2021, methodology): “We use these datasets and evaluate the performance of our methods on the indoor detection [12, 22, 64, 65, 114], scene segmentation [17, 68, 92, 101, 108], and outdoor detection tasks [15, 48, 76–78, 109, 111].”
Geometric Back-Projection Network for Point Cloud Classification (2019, methodology): “[45] continually fed the original 3D coordinates into each layer in their network.”
Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis (2021, methodology): “For each point p , the neighborhood N = { p 1 , · · · , p k } is ﬁrst grouped by a deterministic rule, and KNN is the most frequently used grouping algorithm [6, 44, 21, 47] due to its computational efﬁciency.”
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (2021, methodology): “Prior work has stated that “convolution operation of these methods lacks the ability to capture nonlocally geometric features” (Yan et al., 2020), that a projection-base method “often demands a huge number of views for decent performance” (Liu et al.”
Attention mechanisms in computer vision: A survey (2021, methodology): “[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167”
PCT: Point cloud transformer (2020, neutral): “[33] proposed PointASNL to deal with noise in point cloud processing, using a self-attention mechanism to update features for local groups of points.”
3D Object Detection with Pointformer (2020, methodology): “Compared to the existing local feature extraction modules in [36, 37, 29], the proposed Local Transformer has several advantages.”