Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism

• URL: http://arxiv.org/abs/2203.10569v1
• Date: Sun, 20 Mar 2022 14:42:37 GMT
• Title: Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism
• Authors: Yiming Ren, Peishan Cong, Xinge Zhu, Yuexin Ma
• Abstract summary: Point cloud completion aims to refer the complete shapes for incomplete 3D scans of objects. Current deep learning-based approaches rely on large-scale complete shapes in the training process. We propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data.
• Score: 14.255659581428333
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real scans always miss partial geometries of objects due to the self-occlusions, external-occlusions, and limited sensor resolutions. Point cloud completion aims to refer the complete shapes for incomplete 3D scans of objects. Current deep learning-based approaches rely on large-scale complete shapes in the training process, which are usually obtained from synthetic datasets. It is not applicable for real-world scans due to the domain gap. In this paper, we propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data. Based on the symmetry and similarity of vehicles, we make use of consecutive point cloud frames to construct vehicle memory bank as reference. We design a bottom-up mechanism to focus on both local geometry details and global shape features of inputs. In addition, we design a scene-graph in the network to pay attention to the missing parts by the aid of neighboring vehicles. Experiments show that TraPCC achieve good performance for real-scan completion on KITTI and nuScenes traffic datasets even without any complete data in training. We also show a downstream application of 3D detection, which benefits from our completion approach.

Related papers

• Self-supervised 3D Point Cloud Completion via Multi-view Adversarial Learning [61.14132533712537]
  We propose MAL-SPC, a framework that effectively leverages both object-level and category-specific geometric similarities to complete missing structures. Our MAL-SPC does not require any 3D complete supervision and only necessitates a single partial point cloud for each object.
  arXiv  Detail & Related papers  (2024-07-13T06:53:39Z)
• U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation [19.706172244951116]
  This paper presents U3DS$3$, as a step towards completely unsupervised point cloud segmentation for any holistic 3D scenes. The initial step of our proposed approach involves generating superpoints based on the geometric characteristics of each scene. We then undergo a learning process through a spatial clustering-based methodology, followed by iterative training using pseudo-labels generated in accordance with the cluster centroids.
  arXiv  Detail & Related papers  (2023-11-10T12:05:35Z)
• Point Cloud Completion Guided by Prior Knowledge via Causal Inference [19.935868881427226]
  We propose a novel approach to point cloud completion task called Point-PC. Point-PC uses a memory network to retrieve shape priors and designs a causal inference model to filter missing shape information. Experimental results on the ShapeNet-55, PCN, and KITTI datasets demonstrate that Point-PC outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-28T16:33:35Z)
• 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)
• Towards Confidence-guided Shape Completion for Robotic Applications [6.940242990198]
  Deep learning has begun taking traction as effective means of inferring a complete 3D object representation from partial visual data. We propose an object shape completion method based on an implicit 3D representation providing a confidence value for each reconstructed point. We experimentally validate our approach by comparing reconstructed shapes with ground truths, and by deploying our shape completion algorithm in a robotic grasping pipeline.
  arXiv  Detail & Related papers  (2022-09-09T13:48:24Z)
• Voxel-based Network for Shape Completion by Leveraging Edge Generation [76.23436070605348]
  We develop a voxel-based network for point cloud completion by leveraging edge generation (VE-PCN) We first embed point clouds into regular voxel grids, and then generate complete objects with the help of the hallucinated shape edges. This decoupled architecture together with a multi-scale grid feature learning is able to generate more realistic on-surface details.
  arXiv  Detail & Related papers  (2021-08-23T05:10:29Z)
• Cascaded Refinement Network for Point Cloud Completion with Self-supervision [74.80746431691938]
  We introduce a two-branch network for shape completion. The first branch is a cascaded shape completion sub-network to synthesize complete objects. The second branch is an auto-encoder to reconstruct the original partial input.
  arXiv  Detail & Related papers  (2020-10-17T04:56:22Z)
• VPC-Net: Completion of 3D Vehicles from MLS Point Clouds [16.041815273682317]
  Vehicle Points CompletionNet (VPCNet) We introduce a new encoder module to extract global features from the input instance, consisting of a transformer network and point feature enhancement layer. A new refiner module is also presented to preserve the vehicle details from inputs and refine the complete outputs with fine-grained information.
  arXiv  Detail & Related papers  (2020-08-08T00:22:43Z)
• Point Cloud Completion by Skip-attention Network with Hierarchical Folding [61.59710288271434]
  We propose Skip-Attention Network (SA-Net) for 3D point cloud completion. First, we propose a skip-attention mechanism to effectively exploit the local structure details of incomplete point clouds. Second, in order to fully utilize the selected geometric information encoded by skip-attention mechanism at different resolutions, we propose a novel structure-preserving decoder.
  arXiv  Detail & Related papers  (2020-05-08T06:23:51Z)
• DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes [54.239416488865565]
  We propose a fast single-stage 3D object detection method for LIDAR data. The core novelty of our method is a fast, single-pass architecture that both detects objects in 3D and estimates their shapes. We find that our proposed method achieves state-of-the-art results by 5% on object detection in ScanNet scenes, and it gets top results by 3.4% in the Open dataset.
  arXiv  Detail & Related papers  (2020-04-02T17:48:50Z)

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.