DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentation

• URL: http://arxiv.org/abs/2311.13125v2
• Date: Fri, 26 Apr 2024 03:16:47 GMT
• Title: DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentation
• Authors: Zhiqin Chen, Qimin Chen, Hang Zhou, Hao Zhang,
• Abstract summary: We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset of template parts which are affine-transformed. Our network, coined DAE-Net for Deforming Auto-Encoder, can achieve unsupervised 3D shape co-segmentation that yields fine-grained, compact, and meaningful parts.
• Score: 22.538892330541582
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset of template parts which are affine-transformed. To maximize the expressive power of the part templates, we introduce a per-part deformation network to enable the modeling of diverse parts with substantial geometry variations, while imposing constraints on the deformation capacity to ensure fidelity to the originally represented parts. We also propose a training scheme to effectively overcome local minima. Architecturally, our network is a branched autoencoder, with a CNN encoder taking a voxel shape as input and producing per-part transformation matrices, latent codes, and part existence scores, and the decoder outputting point occupancies to define the reconstruction loss. Our network, coined DAE-Net for Deforming Auto-Encoder, can achieve unsupervised 3D shape co-segmentation that yields fine-grained, compact, and meaningful parts that are consistent across diverse shapes. We conduct extensive experiments on the ShapeNet Part dataset, DFAUST, and an animal subset of Objaverse to show superior performance over prior methods. Code and data are available at https://github.com/czq142857/DAE-Net.

Related papers

• CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization [56.47175002368553]
  This paper introduces a new approach based on a coupled representation and a neural volume optimization to implicitly perform 3D shape editing in latent space. First, we design the coupled neural shape representation for supporting 3D shape editing. Second, we formulate the coupled neural shape optimization procedure to co-optimize the two coupled components in the representation subject to the editing operation.
  arXiv  Detail & Related papers  (2024-02-04T01:52:56Z)
• Attention-based Part Assembly for 3D Volumetric Shape Modeling [0.0]
  We propose a VoxAttention network architecture for attention-based part assembly. Experimental results show that our method outperforms most state-of-the-art methods for the part relation-aware 3D shape modeling task.
  arXiv  Detail & Related papers  (2023-04-17T16:53:27Z)
• Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations [21.59311861556396]
  Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an octree. An encoder-decoder network is designed to learn the adaptive feature volume based on the graph convolutions over the dual graph of octree nodes. Our method effectively encodes shape details, enables fast 3D shape reconstruction, and exhibits good generality for modeling 3D shapes out of training categories.
  arXiv  Detail & Related papers  (2022-05-05T17:56:34Z)
• EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation [19.817166425038753]
  This paper tackles the problem of parts-aware point cloud generation. A simple modification of the Variational Auto-Encoder yields a joint model of the point cloud itself. In addition to the flexibility afforded by our disentangled representation, the inductive bias introduced by our joint modelling approach yields the state-of-the-art experimental results on the ShapeNet dataset.
  arXiv  Detail & Related papers  (2021-10-13T12:38:01Z)
• SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation [50.53931728235875]
  We present SP-GAN, a new unsupervised sphere-guided generative model for direct synthesis of 3D shapes in the form of point clouds. Compared with existing models, SP-GAN is able to synthesize diverse and high-quality shapes with fine details.
  arXiv  Detail & Related papers  (2021-08-10T06:49:45Z)
• Unsupervised 3D Shape Completion through GAN Inversion [116.27680045885849]
  We present ShapeInversion, which introduces Generative Adrial Network (GAN) inversion to shape completion for the first time. ShapeInversion uses a GAN pre-trained on complete shapes by searching for a latent code that gives a complete shape that best fits the given partial input. On the ShapeNet benchmark, the proposed ShapeInversion outperforms the SOTA unsupervised method, and is comparable with supervised methods that are learned using paired data.
  arXiv  Detail & Related papers  (2021-04-27T17:53:46Z)
• CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly [17.82598676258891]
  We introduce CAPRI-Net, a neural network for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models. Our network takes an input 3D shape that can be provided as a point cloud or voxel grids, and reconstructs it by a compact assembly of quadric surface primitives. We evaluate our learning framework on both ShapeNet and ABC, the largest and most diverse CAD dataset to date, in terms of reconstruction quality, shape edges, compactness, and interpretability.
  arXiv  Detail & Related papers  (2021-04-12T17:21:19Z)
• DECOR-GAN: 3D Shape Detailization by Conditional Refinement [50.8801457082181]
  We introduce a deep generative network for 3D shape detailization, akin to stylization with the style being geometric details. We demonstrate that our method can refine a coarse shape into a variety of detailed shapes with different styles.
  arXiv  Detail & Related papers  (2020-12-16T18:52:10Z)
• Neural Subdivision [58.97214948753937]
  This paper introduces Neural Subdivision, a novel framework for data-driven coarseto-fine geometry modeling. We optimize for the same set of network weights across all local mesh patches, thus providing an architecture that is not constrained to a specific input mesh, fixed genus, or category. We demonstrate that even when trained on a single high-resolution mesh our method generates reasonable subdivisions for novel shapes.
  arXiv  Detail & Related papers  (2020-05-04T20:03:21Z)
• Shape-Oriented Convolution Neural Network for Point Cloud Analysis [59.405388577930616]
  Point cloud is a principal data structure adopted for 3D geometric information encoding. Shape-oriented message passing scheme dubbed ShapeConv is proposed to focus on the representation learning of the underlying shape formed by each local neighboring point.
  arXiv  Detail & Related papers  (2020-04-20T16:11:51Z)
• Instant recovery of shape from spectrum via latent space connections [33.83258865005668]
  We introduce the first learning-based method for recovering shapes from Laplacian spectra. Given an auto-encoder, our model takes the form of a cycle-consistent module to map latent vectors to sequences of eigenvalues. Our data-driven approach replaces the need for ad-hoc regularizers required by prior methods, while providing more accurate results at a fraction of the computational cost.
  arXiv  Detail & Related papers  (2020-03-14T00:48:34Z)

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.