Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DiffusionNet: Discretization Agnostic Learning on Surfaces

About

We introduce a new general-purpose approach to deep learning on 3D surfaces, based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in resolution and sampling of a surface -- a basic property which is crucial for practical applications. Our networks can be discretized on various geometric representations such as triangle meshes or point clouds, and can even be trained on one representation then applied to another. We optimize the spatial support of diffusion as a continuous network parameter ranging from purely local to totally global, removing the burden of manually choosing neighborhood sizes. The only other ingredients in the method are a multi-layer perceptron applied independently at each point, and spatial gradient features to support directional filters. The resulting networks are simple, robust, and efficient. Here, we focus primarily on triangle mesh surfaces, and demonstrate state-of-the-art results for a variety of tasks including surface classification, segmentation, and non-rigid correspondence.

Nicholas Sharp, Souhaib Attaiki, Keenan Crane, Maks Ovsjanikov• 2020

Related benchmarks

TaskDatasetResultRank
Mesh Saliency PredictionProposed Dataset Non-textured 1.0 (test)
CC0.4662
45
Mesh Saliency PredictionProposed Dataset Textured Mesh 1.0 (test)
CC0.4351
45
Non-isometric 3D shape matchingSMAL
Mean Geodesic Error6.6
22
Mesh SegmentationHuman Body dataset
Accuracy95.5
20
Near-isometric shape matchingSCAPE (final 20 shapes)
Pointwise Geodesic Error2.9
16
Near-isometric shape matchingFAUST (last 20 shapes)
Pointwise Geodesic Error2.6
16
Non-rigid shape matchingSCAPE
Mean Geodesic Error2.6
16
Saliency PredictionSAL3D (test)
CC0.5371
15
SegmentationHuman Body 12k-vertex meshes
Accuracy90.3
14
Shape classificationSHREC-11 30-class
Accuracy99.4
14
Showing 10 of 20 rows

Other info

Follow for update