Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme

• URL: http://arxiv.org/abs/2103.06134v1
• Date: Wed, 10 Mar 2021 15:32:04 GMT
• Title: Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme
• Authors: Jean-Baptiste Weibel, Timothy Patten, Markus Vincze
• Abstract summary: Learning from artificial 3D models alleviates the cost of annotation necessary to approach this problem. We conjecture that the cause of those issue is the fact that many methods learn directly from point coordinates, instead of the shape. We introduce spherical kernel point convolutions that directly exploit the object surface, represented as a graph, and a voting scheme to limit the impact of poor segmentation.
• Score: 28.072144989298298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While object semantic understanding is essential for most service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates the cost of annotation necessary to approach this problem, but most methods still struggle with the differences existing between artificial and real 3D data. We conjecture that the cause of those issue is the fact that many methods learn directly from point coordinates, instead of the shape, as the former is hard to center and to scale under variable occlusions reliably. We introduce spherical kernel point convolutions that directly exploit the object surface, represented as a graph, and a voting scheme to limit the impact of poor segmentation on the classification results. Our proposed approach improves upon state-of-the-art methods by up to 36% when transferring from artificial objects to real objects.

Related papers

• NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization [80.3424839706698]
  We present NeurOCS, a framework that uses instance masks 3D boxes as input to learn 3D object shapes by means of differentiable rendering. Our approach rests on insights in learning a category-level shape prior directly from real driving scenes. We make critical design choices to learn object coordinates more effectively from an object-centric view.
  arXiv  Detail & Related papers  (2023-05-28T16:18:41Z)
• BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects [89.2314092102403]
  We present a near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence. Our method works for arbitrary rigid objects, even when visual texture is largely absent.
  arXiv  Detail & Related papers  (2023-03-24T17:13:49Z)
• 3D Surface Reconstruction in the Wild by Deforming Shape Priors from Synthetic Data [24.97027425606138]
  Reconstructing the underlying 3D surface of an object from a single image is a challenging problem. We present a new method for joint category-specific 3D reconstruction and object pose estimation from a single image. Our approach achieves state-of-the-art reconstruction performance across several real-world datasets.
  arXiv  Detail & Related papers  (2023-02-24T20:37:27Z)
• InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation [51.121731449575776]
  We develop a novel Incremental 3D Object Recognition Network (i.e., InOR-Net) to recognize new classes of 3D objects continuously. Specifically, a category-guided geometric reasoning is proposed to reason local geometric structures with distinctive 3D characteristics of each class. We then propose a novel critic-induced geometric attention mechanism to distinguish which 3D geometric characteristics within each class are beneficial to overcome the catastrophic forgetting on old classes of 3D objects.
  arXiv  Detail & Related papers  (2023-02-20T10:30:16Z)
• Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objects [0.0]
  We propose a novel semantic 3D object-parts segmentation method that has the flexibility of Local-HDP. We show that the proposed method has a higher percentage of mean intersection over union, using a smaller number of learning instances. We show that the resulting model produces an explicit set of explanations for the 3D object category recognition task.
  arXiv  Detail & Related papers  (2023-01-17T17:43:46Z)
• End-to-End Learning of Multi-category 3D Pose and Shape Estimation [128.881857704338]
  We propose an end-to-end method that simultaneously detects 2D keypoints from an image and lifts them to 3D. The proposed method learns both 2D detection and 3D lifting only from 2D keypoints annotations. In addition to being end-to-end in image to 3D learning, our method also handles objects from multiple categories using a single neural network.
  arXiv  Detail & Related papers  (2021-12-19T17:10:40Z)
• KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control [64.46042014759671]
  KeypointDeformer is an unsupervised method for shape control through automatically discovered 3D keypoints. Our approach produces intuitive and semantically consistent control of shape deformations.
  arXiv  Detail & Related papers  (2021-04-22T17:59:08Z)
• OCM3D: Object-Centric Monocular 3D Object Detection [35.804542148335706]
  We propose a novel object-centric voxel representation tailored for monocular 3D object detection. Specifically, voxels are built on each object proposal, and their sizes are adaptively determined by the 3D spatial distribution of the points. Our method outperforms state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2021-04-13T09:15:40Z)
• Concentric Spherical GNN for 3D Representation Learning [53.45704095146161]
  We propose a novel multi-resolution convolutional architecture for learning over concentric spherical feature maps. Our hierarchical architecture is based on alternatively learning to incorporate both intra-sphere and inter-sphere information. We demonstrate the effectiveness of our approach in improving state-of-the-art performance on 3D classification tasks with rotated data.
  arXiv  Detail & Related papers  (2021-03-18T19:05:04Z)

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.