Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks

• URL: http://arxiv.org/abs/2007.11679v4
• Date: Sun, 3 Oct 2021 20:09:41 GMT
• Title: Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks
• Authors: Kirill Mazur, Victor Lempitsky
• Abstract summary: We present a new versatile building block for deep point cloud processing architectures. This building block combines the ideas of transformers and multi-view convolutional networks with the efficiency of standard convolutional layers. We build architectures for both discriminative (point cloud segmentation, point cloud classification) and generative (point cloud inpainting and image-based point cloud reconstruction) tasks.
• Score: 4.116129791139246
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the efficiency of standard convolutional layers in two and three-dimensional dense grids. The new block operates via multiple parallel heads, whereas each head differentiably rasterizes feature representations of individual points into a low-dimensional space, and then uses dense convolution to propagate information across points. The results of the processing of individual heads are then combined together resulting in the update of point features. Using the new block, we build architectures for both discriminative (point cloud segmentation, point cloud classification) and generative (point cloud inpainting and image-based point cloud reconstruction) tasks. The resulting architectures achieve state-of-the-art performance for these tasks, demonstrating the versatility of the new block for point cloud processing.

Related papers

• Point Cloud Compression with Implicit Neural Representations: A Unified Framework [54.119415852585306]
  We present a pioneering point cloud compression framework capable of handling both geometry and attribute components. Our framework utilizes two coordinate-based neural networks to implicitly represent a voxelized point cloud. Our method exhibits high universality when contrasted with existing learning-based techniques.
  arXiv  Detail & Related papers  (2024-05-19T09:19:40Z)
• Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network [22.9434434107516]
  We develop a new multi-layer transformer network for few-shot point cloud semantic segmentation. Our method achieves the new state-of-the-art performance, with 15% less inference time, over existing few-shot 3D point cloud segmentation models.
  arXiv  Detail & Related papers  (2023-03-28T00:27:54Z)
• AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers [94.11915008006483]
  We present a new method that reformulates point cloud completion as a set-to-set translation problem. We design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion. Our method attains 6.53 CD on PCN, 0.81 CD on ShapeNet-55 and 0.392 MMD on real-world KITTI.
  arXiv  Detail & Related papers  (2023-01-11T16:14:12Z)
• Point Cloud Semantic Segmentation using Multi Scale Sparse Convolution Neural Network [0.0]
  We propose a feature extraction module based on multi-scale ultra-sparse convolution and a feature selection module based on channel attention. By introducing multi-scale sparse convolution, network could capture richer feature information based on convolution kernels of different sizes.
  arXiv  Detail & Related papers  (2022-05-03T15:01:20Z)
• 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)
• Deep Point Cloud Reconstruction [74.694733918351]
  Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. We propose a deep point cloud reconstruction network consisting of two stages: 1) a 3D sparse stacked-hourglass network as for the initial densification and denoising, 2) a refinement via transformers converting the discrete voxels into 3D points.
  arXiv  Detail & Related papers  (2021-11-23T07:53:28Z)
• PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers [81.71904691925428]
  We present a new method that reformulates point cloud completion as a set-to-set translation problem. We also design a new model, called PoinTr, that adopts a transformer encoder-decoder architecture for point cloud completion. Our method outperforms state-of-the-art methods by a large margin on both the new benchmarks and the existing ones.
  arXiv  Detail & Related papers  (2021-08-19T17:58:56Z)
• DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation [45.768040873409824]
  DRINet serves as the basic network structure for dual-representation learning. Our network achieves state-of-the-art results for point cloud classification and segmentation tasks. For large-scale outdoor scenarios, our method outperforms state-of-the-art methods with a real-time inference speed of 62ms per frame.
  arXiv  Detail & Related papers  (2021-08-09T13:23:54Z)
• GRNet: Gridding Residual Network for Dense Point Cloud Completion [54.43648460932248]
  Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. We propose a novel Gridding Residual Network (GRNet) for point cloud completion. Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks.
  arXiv  Detail & Related papers  (2020-06-06T02:46:39Z)

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.