CloudWalker: Random walks for 3D point cloud shape analysis
Point clouds are gaining prominence as a method for representing 3D shapes, but their irregular structure poses a challenge for deep learning methods. In this paper we propose CloudWalker, a novel method for learning 3D shapes using random walks. Previous works attempt to adapt Convolutional Neural Networks (CNNs) or impose a grid or mesh structure to 3D point clouds. This work presents a different approach for representing and learning the shape from a given point set. The key idea is to impose structure on the point set by multiple random walks through the cloud for exploring different regions of the 3D object. Then we learn a per-point and per-walk representation and aggregate multiple walk predictions at inference. Our approach achieves state-of-the-art results for two 3D shape analysis tasks: classification and retrieval.
Code (1)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
MeshWalker: Deep Mesh Understanding by Random Walks
Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a …
3D Classification3D Object RecognitionSemantic SegmentationWalk in the Cloud: Learning Curves for Point Clouds Shape Analysis
Discrete point cloud objects lack sufficient shape descriptors of 3D geometries. In this paper, we present a novel method for aggregating hypothetical curves in point clouds. Sequences of connected points (curves) are in…
3D Part Segmentation3D Point Cloud ClassificationGeneral ClassificationPoint Cloud ClassificationAttWalk: Attentive Cross-Walks for Deep Mesh Analysis
Mesh representation by random walks has been shown to benefit deep learning. Randomness is indeed a powerful concept. However, it comes with a price: some walks might wander around non-characteristic regions of the mesh,…
RetrievalHierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model
In this paper we present SA-CNN, a hierarchical and lightweight self-attention based encoding and decoding architecture for representation learning of point cloud data. The proposed SA-CNN introduces convolution and tran…
Representation LearningRetrievalLearning Gradient Fields for Shape Generation
In this work, we propose a novel technique to generate shapes from point cloud data. A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape. Po…
Point Cloud Generation