DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing

By Yongcheng Liu, Bin Fan, Gaofeng Meng, Jiwen Lu, Shiming Xiang, Chunhong Pan. IEEE International Conference on Computer Vision, 2019

299 citations recorded by the source corpus.

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to this. Here we propose DensePoint, a general architecture to learn densely contextual representation for point cloud processing. Technically, it extends regular grid CNN to irregular point configuration by generalizing a convolution operator, which holds the permutation invariance of points, and achieves efficient inductive learning of local patterns. Architecturally, it finds inspiration from dense connection mode, to repeatedly aggregate multi-level and multi-scale semantics in a deep hierarchy. As a result, densely contextual information along with rich semantics, can be acquired by DensePoint in an organic manner, making it highly effective. Extensive experiments on challenging benchmarks across four tasks, as well as thorough model analysis, verify DensePoint achieves the state of the arts.

View Paper: https://www.semanticscholar.org/paper/b42b1ba256783184f714cc27ececbfb52e247f34

How researchers see this paper

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

Citations in the corpus

Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework (2022, methodology): “Different from the models with sophisticated local geometric extractors (e.g., DeepGCNs (Li et al., 2019), RSCNN (Liu et al., 2019b), RPNet (Ran et al., 2021).)”
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (2021, methodology): “…nonlocally geometric fea-tures” (Yan et al., 2020), that a projection-base method “often demands a huge number of views for decent per-formance” (Liu et al., 2019c), and that projection-based methods often “ﬁne-tune a pre-trained image-based architecture for accurate recognition” (Liu et…”
Stratified Transformer for 3D Point Cloud Segmentation (2022, unknown): “…82.3 85.2 SubSparseCNN [15] 83.3 86.0 PointCNN [22] 84.6 86.1 PointConv [52] 82.8 85.7 Point2Sequence [23] - 85.2 PVCNN [27] - 86.2 RS-CNN [25] 84.0 86.2 KPConv [41] 85.0 86.2 InterpCNN [30] 84.0 86.3 DensePoint [24] 84.2 86.4 PAConv [54] 84 Point Transformer by a large margin in category mIoU.”
Geometric Back-Projection Network for Point Cloud Classification (2019, unknown): “3 DensePoint [65] coords 1k 92.”
ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding (2022, background): “3D visual understanding research [6, 12, 16, 17, 24, 25] is drawing significant attention in recent years due to the increasing demand of real-world applications such as augmented/virtual reality [1, 27, 31, 46], autonomous driving [23, 57] and robotics [2, 48].”
GRNet: Gridding Residual Network for Dense Point Cloud Completion (2020, methodology): “Besides CNNs on discrete space, several methods [8,15,16,39,40,41,42,43] define convolutional kernels on continuous space.”