Yunlu Chen, Basura Fernando, Hakan Bilen, Matthias Niessner, and Efstratios Gavves. 3d equivariant graph implicit functions. In In Proceedings of the European Conference on Computer Vision (ECCV), 2022.
Abstract:
In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric fine details, and to learn from and generalize to shapes with unseen 3D transformations. To this end, we introduce a novel family of graph implicit functions with equivariant layers that facilitates modeling fine local details and guaranteed robustness to various groups of geometric transformations, through local k-NN graph embeddings with sparse point set observations at multiple resolutions. Our method improves over the existing rotation-equivariant implicit function from 0.69 to 0.89 (IoU) on the ShapeNet reconstruction task. We also show that our equivariant implicit function can be extended to other types of similarity transformations and generalizes to unseen translations and scaling.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - AI Singapore Program
Grant Reference no. : AISG2-RP-2020-016
Overseas Funding: -
This research was supported in part by SAVI/MediFor project, ERC
Starting Grant Scan2CAD (804724) and EPSRC programme grant Visual AI EP/T028572/1