Trainable Pointwise Decoder Module for Point Cloud Segmentation

• URL: http://arxiv.org/abs/2408.01548v1
• Date: Fri, 2 Aug 2024 19:29:35 GMT
• Title: Trainable Pointwise Decoder Module for Point Cloud Segmentation
• Authors: Bike Chen, Chen Gong, Antti Tikanmäki, Juha Röning,
• Abstract summary: Point cloud segmentation (PCS) aims to make per-point predictions and enables robots and autonomous driving cars to understand the environment. We propose a trainable pointwise decoder module (PDM) as the post-processing approach. We also introduce a virtual range image-guided copy-rotate-paste strategy in data augmentation.
• Score: 12.233802912441476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud segmentation (PCS) aims to make per-point predictions and enables robots and autonomous driving cars to understand the environment. The range image is a dense representation of a large-scale outdoor point cloud, and segmentation models built upon the image commonly execute efficiently. However, the projection of the point cloud onto the range image inevitably leads to dropping points because, at each image coordinate, only one point is kept despite multiple points being projected onto the same location. More importantly, it is challenging to assign correct predictions to the dropped points that belong to the classes different from the kept point class. Besides, existing post-processing methods, such as K-nearest neighbor (KNN) search and kernel point convolution (KPConv), cannot be trained with the models in an end-to-end manner or cannot process varying-density outdoor point clouds well, thereby enabling the models to achieve sub-optimal performance. To alleviate this problem, we propose a trainable pointwise decoder module (PDM) as the post-processing approach, which gathers weighted features from the neighbors and then makes the final prediction for the query point. In addition, we introduce a virtual range image-guided copy-rotate-paste (VRCrop) strategy in data augmentation. VRCrop constrains the total number of points and eliminates undesirable artifacts in the augmented point cloud. With PDM and VRCrop, existing range image-based segmentation models consistently perform better than their counterparts on the SemanticKITTI, SemanticPOSS, and nuScenes datasets.

Related papers

• P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising [81.92854168911704]
  We tackle the task of point cloud denoising through a novel framework that adapts Diffusion Schr"odinger bridges to points clouds. Experiments on object datasets show that P2P-Bridge achieves significant improvements over existing methods.
  arXiv  Detail & Related papers  (2024-08-29T08:00:07Z)
• PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations [27.45001809414096]
  PosDiffNet is a model for point cloud registration in 3D computer vision. We leverage a graph neural partial differential equation (PDE) based on Beltrami flow to obtain high-dimensional features. We employ the multi-level correspondence derived from the high feature similarity scores to facilitate alignment between point clouds. We evaluate PosDiffNet on several 3D point cloud datasets, verifying that it achieves state-of-the-art (SOTA) performance for point cloud registration in large fields of view with perturbations.
  arXiv  Detail & Related papers  (2024-01-06T08:58:15Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training [16.825524577372473]
  We introduce a point cloud representation learning framework, based on geometric feature reconstruction. We identify three self-supervised learning objectives to peculiar point clouds, namely centroid prediction, normal estimation, and curvature prediction. Our pipeline is conceptually simple and it consists of two major steps: first, it randomly masks out groups of points, followed by a Transformer-based point cloud encoder.
  arXiv  Detail & Related papers  (2023-05-15T17:14:55Z)
• Variational Relational Point Completion Network for Robust 3D Classification [59.80993960827833]
  Vari point cloud completion methods tend to generate global shape skeletons hence lack fine local details. This paper proposes a variational framework, point Completion Network (VRCNet) with two appealing properties. VRCNet shows great generalizability and robustness on real-world point cloud scans.
  arXiv  Detail & Related papers  (2023-04-18T17:03:20Z)
• EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder [60.52613206271329]
  This paper introduces textbfEfficient textbfPoint textbfCloud textbfLearning (EPCL) for training high-quality point cloud models with a frozen CLIP transformer. Our EPCL connects the 2D and 3D modalities by semantically aligning the image features and point cloud features without paired 2D-3D data.
  arXiv  Detail & Related papers  (2022-12-08T06:27:11Z)
• Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classification [6.40412293456886]
  We propose Point-Voxel based Adaptive (PV-Ada) for robust point cloud classification under various corruptions. Experiments on ModelNet-C dataset demonstrate that PV-Ada outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-10-27T14:49:53Z)
• Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors [0.0]
  We argue that a lack of inspiration from the image domain might be the primary cause of such a gap. We propose a graph convolution-based unit, dubbed Shrinking unit, that can be stacked vertically and horizontally for the design of CNN-like 3D point cloud feature extractors.
  arXiv  Detail & Related papers  (2022-09-26T15:28:31Z)
• REGTR: End-to-end Point Cloud Correspondences with Transformers [79.52112840465558]
  We conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC. We propose an end-to-end framework to directly predict the final set of correspondences. Our approach achieves state-of-the-art performance on 3DMatch and ModelNet benchmarks.
  arXiv  Detail & Related papers  (2022-03-28T06:01:00Z)
• SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [52.20602782690776]
  It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data. We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2020-12-08T14:14:09Z)

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.