Representation-Agnostic Shape Fields
This work addresses the need for efficient and adaptable 3D shape analysis tools in computer vision and graphics, offering a plug-and-play performance booster, though it is incremental as it builds on existing methods.
The paper tackles the problem of 3D shape analysis by introducing Representation-Agnostic Shape Fields (RASF), a generalizable shape embedding module that improves performance across various 3D representations like point clouds, meshes, and voxels, with extensive experiments validating its universal effectiveness.
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