SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images

• URL: http://arxiv.org/abs/2008.05742v3
• Date: Thu, 10 Jun 2021 03:26:02 GMT
• Title: SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images
• Authors: Jiapeng Tang, Xiaoguang Han, Mingkui Tan, Xin Tong, Kui Jia
• Abstract summary: This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. We propose two models, the Skeleton-Based GraphConvolutional Neural Network (SkeGCNN) and the Skeleton-Regularized Deep Implicit Surface Network (SkeDISN) We conduct thorough experiments that verify the efficacy of our proposed SkeletonNet.
• Score: 85.66560542483286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. Existingmethods achieve varying degrees of success by using different surface representations. However, they all have their own drawbacks,and cannot properly reconstruct the surface shapes of complex topologies, arguably due to a lack of constraints on the topologicalstructures in their learning frameworks. To this end, we propose to learn and use the topology-preserved, skeletal shape representationto assist the downstream task of object surface reconstruction from RGB images. Technically, we propose the novelSkeletonNetdesign that learns a volumetric representation of a skeleton via a bridged learning of a skeletal point set, where we use paralleldecoders each responsible for the learning of points on 1D skeletal curves and 2D skeletal sheets, as well as an efficient module ofglobally guided subvolume synthesis for a refined, high-resolution skeletal volume; we present a differentiablePoint2Voxellayer tomake SkeletonNet end-to-end and trainable. With the learned skeletal volumes, we propose two models, the Skeleton-Based GraphConvolutional Neural Network (SkeGCNN) and the Skeleton-Regularized Deep Implicit Surface Network (SkeDISN), which respectivelybuild upon and improve over the existing frameworks of explicit mesh deformation and implicit field learning for the downstream surfacereconstruction task. We conduct thorough experiments that verify the efficacy of our proposed SkeletonNet. SkeGCNN and SkeDISNoutperform existing methods as well, and they have their own merits when measured by different metrics. Additional results ingeneralized task settings further demonstrate the usefulness of our proposed methods. We have made both our implementation codeand the ShapeNet-Skeleton dataset publicly available at ble at https://github.com/tangjiapeng/SkeletonNet.

Related papers

• SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training [110.55093254677638]
  We propose an efficient skeleton sequence learning framework, named Skeleton Sequence Learning (SSL) In this paper, we build an asymmetric graph-based encoder-decoder pre-training architecture named SkeletonMAE. Our SSL generalizes well across different datasets and outperforms the state-of-the-art self-supervised skeleton-based action recognition methods.
  arXiv  Detail & Related papers  (2023-07-17T13:33:11Z)
• 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)
• Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images [12.693545159861857]
  We propose a novel deep reinforcement learning-based approach for 3D object reconstruction from monocular images. The proposed method outperforms the state-of-the-art in terms of visual quality, reconstruction accuracy, and computational time.
  arXiv  Detail & Related papers  (2021-09-24T09:44:22Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• Point2Skeleton: Learning Skeletal Representations from Point Clouds [36.62519847312199]
  We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. We first predict a set of skeletal points by learning a geometric transformation, and then analyze the connectivity of the skeletal points to form skeletal mesh structures.
  arXiv  Detail & Related papers  (2020-12-01T03:04:09Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• KShapeNet: Riemannian network on Kendall shape space for Skeleton based Action Recognition [7.183483982542308]
  We propose a geometry aware deep learning approach for skeleton-based action recognition. Skeletons are first modeled as trajectories on Kendall's shape space and then mapped to the linear tangent space. The resulting structured data are then fed to a deep learning architecture, which includes a layer that optimize over rigid and non rigid transformations.
  arXiv  Detail & Related papers  (2020-11-24T10:14:07Z)
• Skeleton-bridged Point Completion: From Global Inference to Local Adjustment [48.2757171993437]
  We propose a skeleton-bridged point completion network (SK-PCN) for shape completion. Given a partial scan, our method first predicts its 3D skeleton to obtain the global structure. We decouple the shape completion into structure estimation and surface reconstruction, which eases the learning difficulty.
  arXiv  Detail & Related papers  (2020-10-14T22:49:30Z)
• 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)

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.