GeoSpark: Sparking up Point Cloud Segmentation with Geometry Clue

by   Zhening Huang, et al.

Current point cloud segmentation architectures suffer from limited long-range feature modeling, as they mostly rely on aggregating information with local neighborhoods. Furthermore, in order to learn point features at multiple scales, most methods utilize a data-agnostic sampling approach to decrease the number of points after each stage. Such sampling methods, however, often discard points for small objects in the early stages, leading to inadequate feature learning. We believe these issues are can be mitigated by introducing explicit geometry clues as guidance. To this end, we propose GeoSpark, a Plug-in module that incorporates Geometry clues into the network to Spark up feature learning and downsampling. GeoSpark can be easily integrated into various backbones. For feature aggregation, it improves feature modeling by allowing the network to learn from both local points and neighboring geometry partitions, resulting in an enlarged data-tailored receptive field. Additionally, GeoSpark utilizes geometry partition information to guide the downsampling process, where points with unique features are preserved while redundant points are fused, resulting in better preservation of key points throughout the network. We observed consistent improvements after adding GeoSpark to various backbones including PointNet++, KPConv, and PointTransformer. Notably, when integrated with Point Transformer, our GeoSpark module achieves a 74.7 71.5 benchmarks. Code and models will be made publicly available.


EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation

Point cloud patterns are hard to learn because of the implicit local geo...

GAM : Gradient Attention Module of Optimization for Point Clouds Analysis

In point cloud analysis tasks, the existing local feature aggregation de...

3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification

Although accurate and fast point cloud classification is a fundamental t...

LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers

Transformer with its underlying attention mechanism and the ability to c...

Stratified Transformer for 3D Point Cloud Segmentation

3D point cloud segmentation has made tremendous progress in recent years...

Local region-learning modules for point cloud classification

Data organization via forming local regions is an integral part of deep ...

Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions

Three-dimensional object recognition has recently achieved great progres...

Please sign up or login with your details

Forgot password? Click here to reset