Fully Steerable 3D Spherical Neurons

• URL: http://arxiv.org/abs/2106.13863v1
• Date: Wed, 2 Jun 2021 16:30:02 GMT
• Title: Fully Steerable 3D Spherical Neurons
• Authors: Pavlo Melnyk, Michael Felsberg, M{\aa}rten Wadenb\"ack
• Abstract summary: We propose a steerable feed-forward learning-based approach that consists of spherical decision surfaces and operates on point clouds. Due to the inherent geometric 3D structure of our theory, we derive a 3D steerability constraint for its atomic parts. We show how the model parameters are fully steerable at inference time.
• Score: 14.86655504533083
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emerging from low-level vision theory, steerable filters found their counterpart in deep learning. Earlier works used the steering theorems and presented convolutional networks equivariant to rigid transformations. In our work, we propose a steerable feed-forward learning-based approach that consists of spherical decision surfaces and operates on point clouds. Due to the inherent geometric 3D structure of our theory, we derive a 3D steerability constraint for its atomic parts, the hypersphere neurons. Exploiting the rotational equivariance, we show how the model parameters are fully steerable at inference time. The proposed spherical filter banks enable to make equivariant and, after online optimization, invariant class predictions for known synthetic point sets in unknown orientations.

Related papers

• ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
  ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization. This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
  arXiv  Detail & Related papers  (2024-03-15T14:35:05Z)
• Learning to Predict 3D Rotational Dynamics from Images of a Rigid Body with Unknown Mass Distribution [4.386534439007928]
  We present a physics-based neural network model to estimate and predict 3D rotational dynamics from image sequences. We demonstrate the efficacy of our approach on new rotating rigid-body datasets of sequences of synthetic images of rotating objects.
  arXiv  Detail & Related papers  (2023-08-24T17:47:32Z)
• Learning Interpretable Dynamics from Images of a Freely Rotating 3D Rigid Body [1.143707646428782]
  We present a physics-informed neural network model to estimate and predict 3D rotational dynamics from image sequences. We demonstrate the efficacy of our approach on a new rotating rigid-body dataset with sequences of rotating cubes and rectangular prisms with uniform and non-uniform density.
  arXiv  Detail & Related papers  (2022-09-23T00:35:22Z)
• Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons [59.83721247071963]
  We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose. Our encoder is stable and consistent, meaning that the shape encoding is purely pose-invariant. The extracted rotation and translation are able to semantically align different input shapes of the same class to a common canonical pose.
  arXiv  Detail & Related papers  (2022-04-03T21:00:44Z)
• SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes [117.76767853430243]
  We introduce SNARF, which combines the advantages of linear blend skinning for polygonal meshes with neural implicit surfaces. We propose a forward skinning model that finds all canonical correspondences of any deformed point using iterative root finding. Compared to state-of-the-art neural implicit representations, our approach generalizes better to unseen poses while preserving accuracy.
  arXiv  Detail & Related papers  (2021-04-08T17:54:59Z)
• Equivariant Point Network for 3D Point Cloud Analysis [17.689949017410836]
  We propose an effective and practical SE(3) (3D translation and rotation) equivariant network for point cloud analysis. First, we present SE(3) separable point convolution, a novel framework that breaks down the 6D convolution into two separable convolutional operators. Second, we introduce an attention layer to effectively harness the expressiveness of the equivariant features.
  arXiv  Detail & Related papers  (2021-03-25T21:57:10Z)
• 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)
• Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes [86.2129580231191]
  Adjoint Rigid Transform (ART) Network is a neural module which can be integrated with a variety of 3D networks. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks. We will release our code and pre-trained models for further research.
  arXiv  Detail & Related papers  (2021-02-01T20:58:45Z)
• Rotation-Invariant Autoencoders for Signals on Spheres [10.406659081400354]
  We study the problem of unsupervised learning of rotation-invariant representations for spherical images. In particular, we design an autoencoder architecture consisting of $S2$ and $SO(3)$ convolutional layers. Experiments on multiple datasets demonstrate the usefulness of the learned representations on clustering, retrieval and classification applications.
  arXiv  Detail & Related papers  (2020-12-08T15:15:03Z)
• Rotation-Invariant Point Convolution With Multiple Equivariant Alignments [1.0152838128195467]
  We show that using rotation-equivariant alignments, it is possible to make any convolutional layer rotation-invariant. With this core layer, we design rotation-invariant architectures which improve state-of-the-art results in both object classification and semantic segmentation.
  arXiv  Detail & Related papers  (2020-12-07T20:47:46Z)
• Quaternion Equivariant Capsule Networks for 3D Point Clouds [58.566467950463306]
  We present a 3D capsule module for processing point clouds that is equivariant to 3D rotations and translations. We connect dynamic routing between capsules to the well-known Weiszfeld algorithm. Based on our operator, we build a capsule network that disentangles geometry from pose.
  arXiv  Detail & Related papers  (2019-12-27T13:51:17Z)

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.