2 papers
cs.CV2021
AttWalk: Attentive Cross-Walks for Deep Mesh Analysis
Ran Ben Izhak, Alon Lahav, Ayellet Tal
Mesh representation by random walks has been shown to benefit deep learning. Randomness is indeed a powerful concept. However, it comes with a price: some walks might wander around…
cs.CV2020
MeshWalker: Deep Mesh Understanding by Random Walks
Alon Lahav, Ayellet Tal
Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representatio…