Representation-Agnostic Shape Fields

03/19/2022
by   Xiaoyang Huang, et al.
0

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

READ FULL TEXT

page 17

page 18

research
06/20/2022

Voxel-MAE: Masked Autoencoders for Pre-training Large-scale Point Clouds

Mask-based pre-training has achieved great success for self-supervised l...
research
11/10/2021

Theoretical and empirical analysis of a fast algorithm for extracting polygons from signed distance bounds

We investigate an asymptotically fast method for transforming signed dis...
research
11/30/2022

GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation

The recent neural implicit representation-based methods have greatly adv...
research
03/30/2021

Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction

This paper focuses on the task of 4D shape reconstruction from a sequenc...
research
08/03/2020

Shape Adaptor: A Learnable Resizing Module

We present a novel resizing module for neural networks: shape adaptor, a...
research
11/29/2017

Compression for Smooth Shape Analysis

Most 3D shape analysis methods use triangular meshes to discretize both ...
research
09/20/2023

ModelGiF: Gradient Fields for Model Functional Distance

The last decade has witnessed the success of deep learning and the surge...

Please sign up or login with your details

Forgot password? Click here to reset