Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons

• URL: http://arxiv.org/abs/2204.01159v1
• Date: Sun, 3 Apr 2022 21:00:44 GMT
• Title: Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons
• Authors: Oren Katzir, Dani Lischinski, Daniel Cohen-Or
• Abstract summary: 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.
• Score: 59.83721247071963
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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, while the extracted rotation and translation are able to semantically align different input shapes of the same class to a common canonical pose. Specifically, we design an auto-encoder based on Vector Neuron Networks, a rotation-equivariant neural network, whose layers we extend to provide translation-equivariance in addition to rotation-equivariance only. The resulting encoder produces pose-invariant shape encoding by construction, enabling our approach to focus on learning a consistent canonical pose for a class of objects. Quantitative and qualitative experiments validate the superior stability and consistency of our approach.

Related papers

• ESCAPE: Equivariant Shape Completion via Anchor Point Encoding [79.59829525431238]
  We introduce ESCAPE, a framework designed to achieve rotation-equivariant shape completion. ESCAPE employs a distinctive encoding strategy by selecting anchor points from a shape and representing all points as a distance to all anchor points. ESCAPE achieves robust, high-quality reconstructions across arbitrary rotations and translations.
  arXiv  Detail & Related papers  (2024-12-01T20:05:14Z)
• Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform [62.27337227010514]
  We introduce a novel self-supervised Rotation-Invariant 3D correspondence learner with Local Shape Transform, dubbed RIST. RIST learns to establish dense correspondences between shapes even under challenging intra-class variations and arbitrary orientations. RIST demonstrates state-of-the-art performances on 3D part label transfer and semantic keypoint transfer given arbitrarily rotated point cloud pairs.
  arXiv  Detail & Related papers  (2024-04-17T08:09:25Z)
• Rethinking Rotation Invariance with Point Cloud Registration [18.829454172955202]
  We propose an effective framework for rotation invariance learning via three sequential stages, namely rotation-invariant shape encoding, aligned feature integration, and deep feature registration. Experimental results on 3D shape classification, part segmentation, and retrieval tasks prove the feasibility of our work.
  arXiv  Detail & Related papers  (2022-12-31T08:17:09Z)
• Frame Averaging for Equivariant Shape Space Learning [85.42901997467754]
  A natural way to incorporate symmetries in shape space learning is to ask that the mapping to the shape space (encoder) and mapping from the shape space (decoder) are equivariant to the relevant symmetries. We present a framework for incorporating equivariance in encoders and decoders by introducing two contributions.
  arXiv  Detail & Related papers  (2021-12-03T06:41:19Z)
• Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields [95.39603371087921]
  Implicit neural representation is a recent approach to learn shape collections as zero level-sets of neural networks. We advocate deformation-aware regularization for implicit neural representations, aiming at producing plausible deformations as latent code changes.
  arXiv  Detail & Related papers  (2021-08-19T22:07:08Z)
• Learning 3D Dense Correspondence via Canonical Point Autoencoder [108.20735652143787]
  We propose a canonical point autoencoder (CPAE) that predicts dense correspondences between 3D shapes of the same category. The autoencoder performs two key functions: (a) encoding an arbitrarily ordered point cloud to a canonical primitive, and (b) decoding the primitive back to the original input instance shape.
  arXiv  Detail & Related papers  (2021-07-10T15:54:48Z)
• 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)

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.