Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly

• URL: http://arxiv.org/abs/2309.06810v2
• Date: Mon, 18 Dec 2023 05:48:04 GMT
• Title: Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly
• Authors: Ruihai Wu, Chenrui Tie, Yushi Du, Yan Zhao, Hao Dong
• Abstract summary: Shape assembly aims to reassemble parts (or fragments) into a complete object. Shape pose disentanglement of part representations is beneficial to geometric shape assembly. We propose to leverage SE(3) equivariance for such shape pose disentanglement.
• Score: 7.4109730384078025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Shape assembly aims to reassemble parts (or fragments) into a complete object, which is a common task in our daily life. Different from the semantic part assembly (e.g., assembling a chair's semantic parts like legs into a whole chair), geometric part assembly (e.g., assembling bowl fragments into a complete bowl) is an emerging task in computer vision and robotics. Instead of semantic information, this task focuses on geometric information of parts. As the both geometric and pose space of fractured parts are exceptionally large, shape pose disentanglement of part representations is beneficial to geometric shape assembly. In our paper, we propose to leverage SE(3) equivariance for such shape pose disentanglement. Moreover, while previous works in vision and robotics only consider SE(3) equivariance for the representations of single objects, we move a step forward and propose leveraging SE(3) equivariance for representations considering multi-part correlations, which further boosts the performance of the multi-part assembly. Experiments demonstrate the significance of SE(3) equivariance and our proposed method for geometric shape assembly. Project page: https://crtie.github.io/SE-3-part-assembly/

Related papers

• 3D Geometric Shape Assembly via Efficient Point Cloud Matching [59.241448711254485]
  We introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad.
  arXiv  Detail & Related papers  (2024-07-15T08:50:02Z)
• 3D Part Assembly Generation with Instance Encoded Transformer [22.330218525999857]
  We propose a multi-layer transformer-based framework that involves geometric and relational reasoning between parts to update the part poses iteratively. We extend our framework to a new task called in-process part assembly. Our method achieves far more than 10% improvements over the current state-of-the-art in multiple metrics on the public PartNet dataset.
  arXiv  Detail & Related papers  (2022-07-05T02:40:57Z)
• Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors [45.187868277839314]
  We introduce a novel task, pairwise 3D geometric shape mating, and propose Neural Shape Mating (NSM) to tackle this problem. Given the point clouds of two object parts of an unknown category, NSM learns to reason about the fit of the two parts and predict a pair of 3D poses that tightly mate them together. We present a self-supervised data collection pipeline that generates pairwise shape mating data with ground truth by randomly cutting an object mesh into two parts.
  arXiv  Detail & Related papers  (2022-05-30T06:58:01Z)
• 3D Compositional Zero-shot Learning with DeCompositional Consensus [102.7571947144639]
  We argue that part knowledge should be composable beyond the observed object classes. We present 3D Compositional Zero-shot Learning as a problem of part generalization from seen to unseen object classes.
  arXiv  Detail & Related papers  (2021-11-29T16:34:53Z)
• Discovering 3D Parts from Image Collections [98.16987919686709]
  We tackle the problem of 3D part discovery from only 2D image collections. Instead of relying on manually annotated parts for supervision, we propose a self-supervised approach. Our key insight is to learn a novel part shape prior that allows each part to fit an object shape faithfully while constrained to have simple geometry.
  arXiv  Detail & Related papers  (2021-07-28T20:29:16Z)
• Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud [50.56461318879761]
  We propose Geometry-Disentangled Attention Network (GDANet) for 3D image processing. GDANet disentangles point clouds into contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components. Experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters.
  arXiv  Detail & Related papers  (2020-12-20T13:35:00Z)
• SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform [49.51977253452456]
  We present an efficient method for 3D shape segmentation based on the medial axis transform (MAT) of the input shape. Specifically, with the rich geometrical and structural information encoded in the MAT, we are able to identify the various types of junctions between different parts of a 3D shape. Our method outperforms the state-of-the-art methods in terms of segmentation quality and is also one order of magnitude faster.
  arXiv  Detail & Related papers  (2020-10-22T07:15:23Z)
• Generative 3D Part Assembly via Dynamic Graph Learning [34.108515032411695]
  Part assembly is a challenging yet crucial task in 3D computer vision and robotics. We propose an assembly-oriented dynamic graph learning framework that leverages an iterative graph neural network as a backbone.
  arXiv  Detail & Related papers  (2020-06-14T04:26:42Z)
• Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [102.44347847154867]
  We propose a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.
  arXiv  Detail & Related papers  (2020-04-02T17:58:05Z)
• Learning 3D Part Assembly from a Single Image [20.175502864488493]
  We introduce a novel problem, single-image-guided 3D part assembly, along with a learningbased solution. We study this problem in the setting of furniture assembly from a given complete set of parts and a single image depicting the entire assembled object.
  arXiv  Detail & Related papers  (2020-03-21T21:19:28Z)

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.