StructRe: Rewriting for Structured Shape Modeling

• URL: http://arxiv.org/abs/2311.17510v4
• Date: Thu, 17 Apr 2025 02:46:59 GMT
• Title: StructRe: Rewriting for Structured Shape Modeling
• Authors: Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Taku Komura, Wenping Wang,
• Abstract summary: We present StructRe, a structure rewriting system, as a novel approach to structured shape modeling.<n>Given a 3D object represented by points and components, StructRe can rewrite it upward into more concise structures, or downward into more detailed structures.
• Score: 60.20359722058389
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Man-made 3D shapes are naturally organized in parts and hierarchies; such structures provide important constraints for shape reconstruction and generation. Modeling shape structures is difficult, because there can be multiple hierarchies for a given shape, causing ambiguity, and across different categories the shape structures are correlated with semantics, limiting generalization. We present StructRe, a structure rewriting system, as a novel approach to structured shape modeling. Given a 3D object represented by points and components, StructRe can rewrite it upward into more concise structures, or downward into more detailed structures; by iterating the rewriting process, hierarchies are obtained. Such a localized rewriting process enables probabilistic modeling of ambiguous structures and robust generalization across object categories. We train StructRe on PartNet data and show its generalization to cross-category and multiple object hierarchies, and test its extension to ShapeNet. We also demonstrate the benefits of probabilistic and generalizable structure modeling for shape reconstruction, generation and editing tasks.

Related papers

• Hierarchical Neural Semantic Representation for 3D Semantic Correspondence [72.8101601086805]
  We design the hierarchical neural semantic representation (HNSR), which consists of a global semantic feature to capture high-level structure and multi-resolution local geometric features.<n>Second, we design a progressive global-to-local matching strategy, which establishes coarse semantic correspondence using the global semantic feature.<n>Third, our framework is training-free and broadly compatible with various pre-trained 3D generative backbones, demonstrating strong generalization across diverse shape categories.
  arXiv  Detail & Related papers  (2025-09-22T07:23:07Z)
• Parameterize Structure with Differentiable Template for 3D Shape Generation [39.414253821696846]
  Recent 3D shape generation works employ complicated networks and structure definitions. We propose a method that parameterizes the shared structure in the same category using a differentiable template. Our method can reconstruct or generate diverse shapes with complicated details, and interpolate them smoothly.
  arXiv  Detail & Related papers  (2024-10-14T11:43:02Z)
• DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects [12.713770164154461]
  We present a novel unsupervised structural reconstruction method, named DPF-Net, based on a new Deformable Primitive Field representation. The strong shape prior encoded in parameterized geometric primitives enables our DPF-Net to extract high-level structures and recover fine-grained shape details consistently.
  arXiv  Detail & Related papers  (2023-08-25T07:50:59Z)
• Grokking of Hierarchical Structure in Vanilla Transformers [72.45375959893218]
  We show that transformer language models can learn to generalize hierarchically after training for extremely long periods. intermediate-depth models generalize better than both very deep and very shallow transformers.
  arXiv  Detail & Related papers  (2023-05-30T04:34:13Z)
• DepGraph: Towards Any Structural Pruning [68.40343338847664]
  We study general structural pruning of arbitrary architecture like CNNs, RNNs, GNNs and Transformers. We propose a general and fully automatic method, emphDependency Graph (DepGraph), to explicitly model the dependency between layers and comprehensively group parameters for pruning. In this work, we extensively evaluate our method on several architectures and tasks, including ResNe(X)t, DenseNet, MobileNet and Vision transformer for images, GAT for graph, DGCNN for 3D point cloud, alongside LSTM for language, and demonstrate that, even with a
  arXiv  Detail & Related papers  (2023-01-30T14:02:33Z)
• Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes [52.038346313823524]
  This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology. Our method is able to produce high-quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-10T08:32:57Z)
• LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies [5.173975064973631]
  We introduce LSD-StructureNet, an augmentation to the StructureNet architecture that enables re-generation of parts. We evaluate LSD-StructureNet on the PartNet dataset, the largest dataset of 3D shapes represented by hierarchies of parts.
  arXiv  Detail & Related papers  (2021-08-18T15:05:06Z)
• DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation [98.96086261213578]
  We introduce DSG-Net, a deep neural network that learns a disentangled structured and geometric mesh representation for 3D shapes. This supports a range of novel shape generation applications with disentangled control, such as of structure (geometry) while keeping geometry (structure) unchanged. Our method not only supports controllable generation applications but also produces high-quality synthesized shapes, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-12T17:06:51Z)
• STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image [27.885717341244014]
  3D reconstruction from a single view image is a long-standing prob-lem in computer vision. In this paper, we propose a novel methodcalled STD-Net to reconstruct the 3D models utilizing the mesh representation. Experimental results on the images from ShapeNet show that ourproposed STD-Net has better performance than other state-of-the-art methods onreconstructing 3D objects.
  arXiv  Detail & Related papers  (2020-03-07T11:02:47Z)
• Unsupervised Learning of Intrinsic Structural Representation Points [50.92621061405056]
  Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points.
  arXiv  Detail & Related papers  (2020-03-03T17:40:00Z)

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.