PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees

• URL: http://arxiv.org/abs/2208.05962v1
• Date: Thu, 11 Aug 2022 17:59:09 GMT
• Title: PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees
• Authors: Jun-Kun Chen and Yu-Xiong Wang
• Abstract summary: We propose PointTree, a point cloud encoder that is robust to transformations based on relaxed K-D trees. Key to our approach is the design of the division rule in K-D trees by using principal component analysis (PCA) In addition to this novel architecture design, we further improve the introducing by pre-alignment.
• Score: 27.641101804012152
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Being able to learn an effective semantic representation directly on raw point clouds has become a central topic in 3D understanding. Despite rapid progress, state-of-the-art encoders are restrictive to canonicalized point clouds, and have weaker than necessary performance when encountering geometric transformation distortions. To overcome this challenge, we propose PointTree, a general-purpose point cloud encoder that is robust to transformations based on relaxed K-D trees. Key to our approach is the design of the division rule in K-D trees by using principal component analysis (PCA). We use the structure of the relaxed K-D tree as our computational graph, and model the features as border descriptors which are merged with pointwise-maximum operation. In addition to this novel architecture design, we further improve the robustness by introducing pre-alignment -- a simple yet effective PCA-based normalization scheme. Our PointTree encoder combined with pre-alignment consistently outperforms state-of-the-art methods by large margins, for applications from object classification to semantic segmentation on various transformed versions of the widely-benchmarked datasets. Code and pre-trained models are available at https://github.com/immortalCO/PointTree.

Related papers

• Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression [39.052583172727324]
  The Geometry-based Point Cloud Compression (G-PCC) has been developed by the Moving Picture Experts Group to compress point clouds. This paper proposes a hierarchical prior-based super resolution method for point cloud geometry compression.
  arXiv  Detail & Related papers  (2024-02-17T11:15:38Z)
• Point Cloud Compression with Sibling Context and Surface Priors [47.96018990521301]
  We present a novel octree-based multi-level framework for large-scale point cloud compression. In this framework, we propose a new entropy model that explores the hierarchical dependency in an octree. We locally fit surfaces with a voxel-based geometry-aware module to provide geometric priors in entropy encoding.
  arXiv  Detail & Related papers  (2022-05-02T09:13:26Z)
• Learning Local Displacements for Point Cloud Completion [93.54286830844134]
  We propose a novel approach aimed at object and semantic scene completion from a partial scan represented as a 3D point cloud. Our architecture relies on three novel layers that are used successively within an encoder-decoder structure. We evaluate both architectures on object and indoor scene completion tasks, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-30T18:31:37Z)
• PointAttN: You Only Need Attention for Point Cloud Completion [89.88766317412052]
  Point cloud completion refers to completing 3D shapes from partial 3D point clouds. We propose a novel neural network for processing point cloud in a per-point manner to eliminate kNNs. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes.
  arXiv  Detail & Related papers  (2022-03-16T09:20:01Z)
• OctAttention: Octree-based Large-scale Contexts Model for Point Cloud Compression [36.77271904751208]
  OctAttention employs the octree structure, a memory-efficient representation for point clouds. Our approach saves 95% coding time compared to the voxel-based baseline. Compared to the previous state-of-the-art works, our approach obtains a 10%-35% BD-Rate gain on the LiDAR benchmark.
  arXiv  Detail & Related papers  (2022-02-12T10:06:12Z)
• CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning [53.1436669083784]
  We propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in the point cloud. For classification, we get a competitive result with the fully-supervised methods on ModelNet40 (92.5% accuracy) and ScanObjectNN (87.9% accuracy)
  arXiv  Detail & Related papers  (2022-01-20T15:04:12Z)
• Robust Partial-to-Partial Point Cloud Registration in a Full Range [12.86951061306046]
  We propose Graph Matching Consensus Network (GMCNet), which estimates pose-invariant correspondences for fullrange 1 Partial-to-Partial point cloud Registration (PPR) GMCNet encodes point descriptors for each point cloud individually without using crosscontextual information, or ground truth correspondences for training.
  arXiv  Detail & Related papers  (2021-11-30T17:56:24Z)
• DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction [29.191330510706408]
  We present a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction. Our method, termed Deep Point Correspondence (DPC), requires a fraction of the training data compared to previous techniques. Our construction scheme leads to a performance boost in comparison to recent state-of-the-art correspondence methods.
  arXiv  Detail & Related papers  (2021-10-16T18:41:13Z)
• UPDesc: Unsupervised Point Descriptor Learning for Robust Registration [54.95201961399334]
  UPDesc is an unsupervised method to learn point descriptors for robust point cloud registration. We show that our learned descriptors yield superior performance over existing unsupervised methods.
  arXiv  Detail & Related papers  (2021-08-05T17:11:08Z)
• Rethinking Learnable Tree Filter for Generic Feature Transform [71.77463476808585]
  Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. To relax the geometric constraint, we give the analysis by reformulating it as a Markov Random Field and introduce a learnable unary term. For semantic segmentation, we achieve leading performance (82.1% mIoU) on the Cityscapes benchmark without bells-and-whistles.
  arXiv  Detail & Related papers  (2020-12-07T07:16:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.