Representation-Agnostic Shape Fields

• URL: http://arxiv.org/abs/2203.10259v1
• Date: Sat, 19 Mar 2022 06:54:45 GMT
• Title: Representation-Agnostic Shape Fields
• Abstract summary: We present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning. Based on RASF, shape embeddings for various 3D shape representations (point clouds, meshes and voxels) are retrieved by coordinate indexing. Once trained, RASF becomes a plug-and-play performance booster with negligible cost.
• Score: 43.123829024621514
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D shape analysis has been widely explored in the era of deep learning. Numerous models have been developed for various 3D data representation formats, e.g., MeshCNN for meshes, PointNet for point clouds and VoxNet for voxels. In this study, we present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning. RASF is implemented with a learnable 3D grid with multiple channels to store local geometry. Based on RASF, shape embeddings for various 3D shape representations (point clouds, meshes and voxels) are retrieved by coordinate indexing. While there are multiple ways to optimize the learnable parameters of RASF, we provide two effective schemes among all in this paper for RASF pre-training: shape reconstruction and normal estimation. Once trained, RASF becomes a plug-and-play performance booster with negligible cost. Extensive experiments on diverse 3D representation formats, networks and applications, validate the universal effectiveness of the proposed RASF. Code and pre-trained models are publicly available https://github.com/seanywang0408/RASF

Related papers

• FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation [15.58096401866496]
  Deep learning-based 3D medical image segmentation methods relies on large-scale labeled datasets.<n>Formula-Driven Supervised Learning method offers an appealing alternative by generating training data and labels directly from mathematical formulas.<n>We introduce Formula-Driven supervised learning with Implicit Functions (FDIF), a framework that enables scalable pre-training without using any real data and medical expert annotations.
  arXiv  Detail & Related papers  (2026-03-24T13:45:39Z)
• Learning Unsigned Distance Fields from Local Shape Functions for 3D Surface Reconstruction [42.840655419509346]
  This paper presents a novel neural framework, LoSF-UDF, for reconstructing surfaces from 3D point clouds by leveraging local shape functions to learn UDFs. We observe that 3D shapes manifest simple patterns within localized areas, prompting us to create a training dataset of point cloud patches. Our approach learns features within a specific radius around each query point and utilizes an attention mechanism to focus on the crucial features for UDF estimation.
  arXiv  Detail & Related papers  (2024-07-01T14:39:03Z)
• Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models [83.35835521670955]
  Surf-D is a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies. We use the Unsigned Distance Field (UDF) as our surface representation to accommodate arbitrary topologies. We also propose a new pipeline that employs a point-based AutoEncoder to learn a compact and continuous latent space for accurately encoding UDF.
  arXiv  Detail & Related papers  (2023-11-28T18:56:01Z)
• MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation [91.6658845016214]
  We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. We render a 3D shape from multiple views, and set up a dense correspondence learning task within the contrastive learning framework. As a result, the learned 2D representations are view-invariant and geometrically consistent.
  arXiv  Detail & Related papers  (2022-08-18T00:48:15Z)
• NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation [7.208066405543874]
  In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. We propose Omni Distance Fields (ODFs), a new 3D shape representation that encodes geometry by storing the depth to the object's surface from any 3D position in any viewing direction.
  arXiv  Detail & Related papers  (2022-06-12T20:59:26Z)
• Neural Vector Fields for Implicit Surface Representation and Inference [73.25812045209001]
  Implicit fields have recently shown increasing success in representing and learning 3D shapes accurately. We develop a novel and yet a fundamental representation considering unit vectors in 3D space and call it Vector Field (VF) We show the advantages of VF representation, in learning open, closed, or multi-layered as well as piecewise planar surfaces.
  arXiv  Detail & Related papers  (2022-04-13T17:53:34Z)
• SurFit: Learning to Fit Surfaces Improves Few Shot Learning on Point Clouds [48.61222927399794]
  SurFit is a simple approach for label efficient learning of 3D shape segmentation networks. It is based on a self-supervised task of decomposing the surface of a 3D shape into geometric primitives.
  arXiv  Detail & Related papers  (2021-12-27T23:55:36Z)
• 3D Shapes Local Geometry Codes Learning with SDF [8.37542758486152]
  A signed distance function (SDF) as the 3D shape description is one of the most effective approaches to represent 3D geometry for rendering and reconstruction. In this paper, we consider the degeneration problem of reconstruction coming from the capacity decrease of the DeepSDF model. We propose Local Geometry Code Learning (LGCL), a model that improves the original DeepSDF results by learning from a local shape geometry.
  arXiv  Detail & Related papers  (2021-08-19T09:56:03Z)
• KAPLAN: A 3D Point Descriptor for Shape Completion [80.15764700137383]
  KAPLAN is a 3D point descriptor that aggregates local shape information via a series of 2D convolutions. In each of those planes, point properties like normals or point-to-plane distances are aggregated into a 2D grid and abstracted into a feature representation with an efficient 2D convolutional encoder. Experiments on public datasets show that KAPLAN achieves state-of-the-art performance for 3D shape completion.
  arXiv  Detail & Related papers  (2020-07-31T21:56:08Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

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.