Mesh Convolution With Continuous Filters for 3-D Surface Parsing

doi:10.1109/TNNLS.2023.3281871

Mesh Convolution With Continuous Filters for 3-D Surface Parsing

2024-10-01

4

OA

AI

DOI：10.1109/TNNLS.2023.3281871

Original

Original request for help

Save

Abstract

En 中文

Geometric feature learning for 3-D surfaces is critical for many applications in computer graphics and 3-D vision. However, deep learning currently lags in hierarchical modeling of 3-D surfaces due to the lack of required operations and/or their efficient implementations. In this article, we propose a series of modular operations for effective geometric feature learning from 3-D triangle meshes. These operations include novel mesh convolutions, efficient mesh decimation, and associated mesh (un)poolings. Our mesh convolutions exploit spherical harmonics as orthonormal bases to create continuous convolutional filters. The mesh decimation module is graphics processing unit (GPU)-accelerated and able to process batched meshes on-the-fly, while the (un)pooling operations compute features for upsampled/downsampled meshes. We provide an open-source implementation of these operations, collectively termed Picasso. Picasso supports heterogeneous mesh batching and processing. Leveraging its modular operations, we further contribute a novel hierarchical neural network for perceptual parsing of 3-D surfaces, named PicassoNet ++ . It achieves highly competitive performance for shape analysis and scene segmentation on prominent 3-D benchmarks. The code, data, and trained models are available at https://github.com/EnyaHermite/Picasso.

Keywords:

Graphics processing unit (GPU) mesh decimation

heterogeneous meshes

mesh convolution

point cloud

spherical harmonics

surface parsing

Mesh Convolution With Continuous Filters for 3-D Surface Parsing

Abstract

Journal

Organization