TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations
Topology matters. Despite the recent success of point cloud processing with geometric deep learning, it remains arduous to capture the complex topologies of point cloud data with a learning model. Given a point cloud dataset containing objects with various genera, or scenes with multiple objects, we propose an autoencoder, TearingNet, which tackles the challenging task of representing the point clouds using a fixed-length descriptor. Unlike existing works directly deforming predefined primitives of genus zero (e.g., a 2D square patch) to an object-level point cloud, our TearingNet is characterized by a proposed Tearing network module and a Folding network module interacting with each other iteratively. Particularly, the Tearing network module learns the point cloud topology explicitly. By breaking the edges of a primitive graph, it tears the graph into patches or with holes to emulate the topology of a target point cloud, leading to faithful reconstructions. Experimentation shows the superiority of our proposal in terms of reconstructing point clouds as well as generating more topology-friendly representations than benchmarks.
Code (1)
Similar Papers 제목 키워드 기반
Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering
We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels an…
3D Point Cloud ReconstructionDecoderGeneral ClassificationPoint cloud reconstructionTopNet: Structural Point Cloud Decoder
3D point cloud generation is of great use for 3D scene modeling and understanding. Real-world 3D object point clouds can be properly described by a collection of low-level and high-level structures such as surf…
DecoderObjectPoint Cloud CompletionLAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints
Point cloud completion aims at completing geometric and topological shapes from a partial observation. However, some topology of the original shape is missing, existing methods directly predict the location of complete p…
Point Cloud CompletionCluster-Based Autoencoders for Volumetric Point Clouds
Autoencoders allow to reconstruct a given input from a small set of parameters. However, the input size is often limited due to computational costs. We therefore propose a clustering and reassembling method for volumetri…
ClusteringHybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generation
Linker generation is critical in drug discovery applications such as lead optimization and PROTAC design, where molecular fragments are assembled into diverse drug candidates via molecular linker. Existing methods fall i…
DiversityDrug Discovery