Point Cloud Segmentation Using Sparse Temporal Local Attention

• URL: http://arxiv.org/abs/2112.00289v2
• Date: Thu, 2 Dec 2021 06:16:52 GMT
• Title: Point Cloud Segmentation Using Sparse Temporal Local Attention
• Authors: Joshua Knights, Peyman Moghadam, Clinton Fookes, Sridha Sridharan
• Abstract summary: We propose a novel Sparse Temporal Local Attention (STELA) module which aggregates intermediate features from a local neighbourhood in previous point cloud frames. We achieve a competitive mIoU of 64.3% on the SemanticKitti dataset, and demonstrate significant improvement over the single-frame baseline.
• Score: 30.969737698335944
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment. However despite the sensor outputs from autonomous vehicles being naturally temporal in nature, there is still limited exploration of exploiting point cloud sequences for 3D seman-tic segmentation. In this paper we propose a novel Sparse Temporal Local Attention (STELA) module which aggregates intermediate features from a local neighbourhood in previous point cloud frames to provide a rich temporal context to the decoder. Using the sparse local neighbourhood enables our approach to gather features more flexibly than those which directly match point features, and more efficiently than those which perform expensive global attention over the whole point cloud frame. We achieve a competitive mIoU of 64.3% on the SemanticKitti dataset, and demonstrate significant improvement over the single-frame baseline in our ablation studies.

Related papers

• FASTC: A Fast Attentional Framework for Semantic Traversability Classification Using Point Cloud [7.711666704468952]
  We address the problem of traversability assessment using point clouds. We propose a pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume. We then propose a newtemporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds.
  arXiv  Detail & Related papers  (2024-06-24T12:01:55Z)
• 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)
• Collect-and-Distribute Transformer for 3D Point Cloud Analysis [82.03517861433849]
  We propose a new transformer network equipped with a collect-and-distribute mechanism to communicate short- and long-range contexts of point clouds. Results show the effectiveness of the proposed CDFormer, delivering several new state-of-the-art performances on point cloud classification and segmentation tasks.
  arXiv  Detail & Related papers  (2023-06-02T03:48:45Z)
• Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation [5.763876449960417]
  Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents. Most state-of-art approaches rely on relatively dense point clouds and performance drops significantly for sparse point clouds. Unsupervised domain adaption allows to minimise the discrepancy between dense and sparse point clouds.
  arXiv  Detail & Related papers  (2022-05-07T13:42:43Z)
• 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)
• Temporal Point Cloud Completion with Pose Disturbance [32.536545112645335]
  We provide complete point clouds from sparse input with pose disturbance by limited translation and rotation. We also use temporal information to enhance the completion model, refining the output with a sequence of inputs. Our framework is the first to utilize temporal information and ensure temporal consistency with limited transformation.
  arXiv  Detail & Related papers  (2022-02-07T11:41:12Z)
• Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion [38.05362492645094]
  Real point cloud scenes can intuitively capture complex surroundings in the real world, but due to 3D data's raw nature, it is very challenging for machine perception. We concentrate on the essential visual task, semantic segmentation, for large-scale point cloud data collected in reality. By comparing with state-of-the-art networks on three different benchmarks, we demonstrate the effectiveness of our network.
  arXiv  Detail & Related papers  (2021-03-12T04:13:20Z)
• ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation [49.15948235059343]
  We further improve point-temporal cloud feature with a flexible module called ASAP. Our ASAP module contains an attentive temporal embedding layer to fuse the relatively informative local features across frames in a recurrent fashion. We show the generalization ability of the proposed ASAP module with different computation backbone networks for point cloud sequence segmentation.
  arXiv  Detail & Related papers  (2020-08-12T07:37:16Z)
• InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling [65.47126868838836]
  We propose a novel 3D object detection framework with dynamic information modeling. Coarse predictions are generated in the first stage via a voxel-based region proposal network. Experiments are conducted on the large-scale nuScenes 3D detection benchmark.
  arXiv  Detail & Related papers  (2020-07-16T18:27:08Z)
• Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds [76.52448276587707]
  We propose Reconfigurable Voxels, a new approach to constructing representations from 3D point clouds. Specifically, we devise a biased random walk scheme, which adaptively covers each neighborhood with a fixed number of voxels. We find that this approach effectively improves the stability of voxel features, especially for sparse regions.
  arXiv  Detail & Related papers  (2020-04-06T15:07:16Z)
• MNEW: Multi-domain Neighborhood Embedding and Weighting for Sparse Point Clouds Segmentation [1.2380933178502298]
  We propose MNEW, including multi-domain neighborhood embedding, and attention weighting based on their geometry distance, feature similarity, and neighborhood sparsity. MNEW achieves the top performance for sparse point clouds, which is important to the application of LiDAR-based automated driving perception.
  arXiv  Detail & Related papers  (2020-04-05T18:02:07Z)

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.