Geometric Reasoning in the Embedding Space

• URL: http://arxiv.org/abs/2504.02018v1
• Date: Wed, 02 Apr 2025 14:13:52 GMT
• Title: Geometric Reasoning in the Embedding Space
• Authors: Jan Hůla, David Mojžíšek, Jiří Janeček, David Herel, Mikoláš Janota,
• Abstract summary: We show that Graph Neural Networks and Transformers can learn to reason about geometric constraints.<n>We train them to predict spatial position of points in a discrete 2D grid from a set of constraints.<n>We also show that the Graph Neural Network we design for the task performs significantly better than the Transformer and is also easier to scale.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this contribution, we demonstrate that Graph Neural Networks and Transformers can learn to reason about geometric constraints. We train them to predict spatial position of points in a discrete 2D grid from a set of constraints that uniquely describe hidden figures containing these points. Both models are able to predict the position of points and interestingly, they form the hidden figures described by the input constraints in the embedding space during the reasoning process. Our analysis shows that both models recover the grid structure during training so that the embeddings corresponding to the points within the grid organize themselves in a 2D subspace and reflect the neighborhood structure of the grid. We also show that the Graph Neural Network we design for the task performs significantly better than the Transformer and is also easier to scale.

Related papers

• GridFormer: Point-Grid Transformer for Surface Reconstruction [37.30776475324579]
  We introduce a novel attention mechanism between the grid and point features named Point-Grid Transformer (GridFormer) This mechanism treats the grid as a transfer point connecting the space and point cloud. We also propose a boundary optimization strategy incorporating margin binary cross-entropy loss and boundary sampling.
  arXiv  Detail & Related papers  (2024-01-04T14:31:56Z)
• Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation [62.258256483231484]
  LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Many works project the point cloud onto the 2D image and adopt the 2D Convolutional Neural Networks (CNNs) or vision transformer for LiDAR point cloud semantic segmentation. In this paper, we propose a novel spherical frustum structure to avoid quantized information loss.
  arXiv  Detail & Related papers  (2023-11-29T09:55:13Z)
• Shape-Graph Matching Network (SGM-net): Registration for Statistical Shape Analysis [20.58923754314197]
  This paper focuses on the statistical analysis of shapes of data objects called shape graphs. A critical need here is a constrained registration of points (nodes to nodes, edges to edges) across objects. This paper tackles this registration problem using a novel neural-network architecture.
  arXiv  Detail & Related papers  (2023-08-14T00:42:03Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• A singular Riemannian geometry approach to Deep Neural Networks II. Reconstruction of 1-D equivalence classes [78.120734120667]
  We build the preimage of a point in the output manifold in the input space. We focus for simplicity on the case of neural networks maps from n-dimensional real spaces to (n - 1)-dimensional real spaces.
  arXiv  Detail & Related papers  (2021-12-17T11:47:45Z)
• Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment [8.325327265120283]
  We provide a novel new approach for aligning geometric models using a dual graph structure where local features are mapping probabilities. We report state of the art results on stretchable domains alignment in a rapid and stable solution for meshes and cloud of points.
  arXiv  Detail & Related papers  (2020-11-30T12:03:28Z)
• Primal-Dual Mesh Convolutional Neural Networks [62.165239866312334]
  We propose a primal-dual framework drawn from the graph-neural-network literature to triangle meshes. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them. We provide theoretical insights of our approach using tools from the mesh-simplification literature.
  arXiv  Detail & Related papers  (2020-10-23T14:49:02Z)
• node2coords: Graph Representation Learning with Wasserstein Barycenters [59.07120857271367]
  We introduce node2coords, a representation learning algorithm for graphs. It learns simultaneously a low-dimensional space and coordinates for the nodes in that space. Experimental results demonstrate that the representations learned with node2coords are interpretable.
  arXiv  Detail & Related papers  (2020-07-31T13:14:25Z)
• Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation [76.21696417873311]
  We introduce a learnable module, cylindrical convolutional networks (CCNs), that exploit cylindrical representation of a convolutional kernel defined in the 3D space. CCNs extract a view-specific feature through a view-specific convolutional kernel to predict object category scores at each viewpoint. Our experiments demonstrate the effectiveness of the cylindrical convolutional networks on joint object detection and viewpoint estimation.
  arXiv  Detail & Related papers  (2020-03-25T10:24:58Z)

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.