Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives

• URL: http://arxiv.org/abs/2503.06947v1
• Date: Mon, 10 Mar 2025 05:52:17 GMT
• Title: Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives
• Authors: Jiaxin Li, Hongxing Wang, Jiawei Tan, Zhilong Ou, Junsong Yuan,
• Abstract summary: Understanding 3D object shapes requires shape representation by object parts abstracted from results of instance and semantic segmentation.<n>We introduce a one-stage, fully unsupervised framework towards semantic-aware shape representation.<n>This framework produces joint instance segmentation, semantic segmentation, and shape abstraction through sparse representation and feature alignment of object parts in a high-dimensional space.
• Score: 48.155145581663724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding 3D object shapes necessitates shape representation by object parts abstracted from results of instance and semantic segmentation. Promising shape representations enable computers to interpret a shape with meaningful parts and identify their repeatability. However, supervised shape representations depend on costly annotation efforts, while current unsupervised methods work under strong semantic priors and involve multi-stage training, thereby limiting their generalization and deployment in shape reasoning and understanding. Driven by the tendency of high-dimensional semantically similar features to lie in or near low-dimensional subspaces, we introduce a one-stage, fully unsupervised framework towards semantic-aware shape representation. This framework produces joint instance segmentation, semantic segmentation, and shape abstraction through sparse representation and feature alignment of object parts in a high-dimensional space. For sparse representation, we devise a sparse latent membership pursuit method that models each object part feature as a sparse convex combination of point features at either the semantic or instance level, promoting part features in the same subspace to exhibit similar semantics. For feature alignment, we customize an attention-based strategy in the feature space to align instance- and semantic-level object part features and reconstruct the input shape using both of them, ensuring geometric reusability and semantic consistency of object parts. To firm up semantic disambiguation, we construct cascade unfrozen learning on geometric parameters of object parts.

Related papers

• Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image [52.11275397911693]
  We propose an end-to-end trainable, cross-category method for reconstructing multiple man-made articulated objects from a single RGBD image. We depart from previous works that rely on learning instance-level latent space, focusing on man-made articulated objects with predefined part counts. Our method successfully reconstructs variously structured multiple instances that previous works cannot handle, and outperforms prior works in shape reconstruction and kinematics estimation.
  arXiv  Detail & Related papers  (2025-04-04T05:08:04Z)
• Structure-Aware Correspondence Learning for Relative Pose Estimation [65.44234975976451]
  Relative pose estimation provides a promising way for achieving object-agnostic pose estimation. Existing 3D correspondence-based methods suffer from small overlaps in visible regions and unreliable feature estimation for invisible regions. We propose a novel Structure-Aware Correspondence Learning method for Relative Pose Estimation, which consists of two key modules.
  arXiv  Detail & Related papers  (2025-03-24T13:43:44Z)
• Instance-aware 3D Semantic Segmentation powered by Shape Generators and Classifiers [28.817905887080293]
  We propose a novel instance-aware approach for 3D semantic segmentation. Our method combines several geometry processing tasks supervised at instance-level to promote the consistency of the learned feature representation.
  arXiv  Detail & Related papers  (2023-11-21T02:14:16Z)
• ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation [47.94499636697971]
  We present ShapeMatcher, a unified self-supervised learning framework for joint shape canonicalization, segmentation, retrieval and deformation. The key insight of ShapeMaker is the simultaneous training of the four highly-associated processes: canonicalization, segmentation, retrieval, and deformation.
  arXiv  Detail & Related papers  (2023-11-18T15:44:57Z)
• Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement [75.9289887536165]
  We present a hierarchical abstraction approach to uncover underlying entities. We show how to learn a correspondence between intervening on states of entities in the agent's model and acting on objects in the environment. We use this correspondence to develop a method for control that generalizes to different numbers and configurations of objects.
  arXiv  Detail & Related papers  (2023-03-20T18:19:36Z)
• Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance [33.10167928198986]
  Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. We present a novel self-supervised strategy that solves this problem without any human labels.
  arXiv  Detail & Related papers  (2023-02-28T03:02:11Z)
• Self-Supervised Learning of Object Parts for Semantic Segmentation [7.99536002595393]
  We argue that self-supervised learning of object parts is a solution to this issue. Our method surpasses the state-of-the-art on three semantic segmentation benchmarks by 17%-3%.
  arXiv  Detail & Related papers  (2022-04-27T17:55:17Z)
• SPAMs: Structured Implicit Parametric Models [30.19414242608965]
  We learn Structured-implicit PArametric Models (SPAMs) as a deformable object representation that structurally decomposes non-rigid object motion into part-based disentangled representations of shape and pose. Experiments demonstrate that our part-aware shape and pose understanding lead to state-of-the-art performance in reconstruction and tracking of depth sequences of complex deforming object motion.
  arXiv  Detail & Related papers  (2022-01-20T12:33:46Z)
• Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds [8.156355030558172]
  Representing complex 3D objects as simple geometric primitives, known as shape abstraction, is important for geometric modeling, structural analysis, and shape synthesis. We propose an unsupervised shape abstraction method to map a point cloud into a compact cuboid representation.
  arXiv  Detail & Related papers  (2021-06-07T09:15:16Z)
• Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks [118.20778308823779]
  We present a novel 3D primitive representation that defines primitives using an Invertible Neural Network (INN) Our model learns to parse 3D objects into semantically consistent part arrangements without any part-level supervision.
  arXiv  Detail & Related papers  (2021-03-18T17:59:31Z)
• Improving Semantic Segmentation via Decoupled Body and Edge Supervision [89.57847958016981]
  Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for semantic segmentation is proposed. Our insight is that appealing performance of semantic segmentation requires textitexplicitly modeling the object textitbody and textitedge, which correspond to the high and low frequency of the image. We show that the proposed framework with various baselines or backbone networks leads to better object inner consistency and object boundaries.
  arXiv  Detail & Related papers  (2020-07-20T12:11:22Z)

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.