Exact Shape Correspondence via 2D graph convolution
Dec 6, 2022
Speakers
About
For exact 3D shape correspondence (matching or alignment), i.e., the task of matching each point on a shape to its exact corresponding point on the other shape (or to be more specific, matching at geodesic error 0), most existing methods do not perform well due to two main problems. First, on nearly-isometric shapes (i.e., low noise levels), most existing methods use the eigen-vectors (eigen-functions) of the Laplace Beltrami Operator (LBO) or other shape descriptors to update an initialized correspondence which is not exact, leading to an accumulation of update errors. Thus, though the final correspondence may generally be smooth, it is generally inexact. Second, on non-isometric shapes (noisy shapes), existing methods are generally not robust to noise as they usually assume near-isometry. In addition, existing methods that attempt to address the non-isometric shape problem (e.g., GRAMPA) are generally computationally expensive and do not generalise to nearly-isometric shapes. To address these two problems, we propose a 2D graph convolution-based framework called 2D-GEM. 2D-GEM is robust to noise on non-isometric shapes and with a few additional constraints, it also addresses the errors in the update on nearly-isometric shapes. We demonstrate the effectiveness of 2D-GEM by achieving a high accuracy of 90.5% at geodesic error 0 on the non-isometric benchmark SHREC16, i.e., TOPKIDS (while being much faster than GRAMPA), and on nearly-isometric benchmarks by achieving a high accuracy of 92.5% on TOSCA and 84.9% on SCAPE at geodesic error 0.For exact 3D shape correspondence (matching or alignment), i.e., the task of matching each point on a shape to its exact corresponding point on the other shape (or to be more specific, matching at geodesic error 0), most existing methods do not perform well due to two main problems. First, on nearly-isometric shapes (i.e., low noise levels), most existing methods use the eigen-vectors (eigen-functions) of the Laplace Beltrami Operator (LBO) or other shape descriptors to update an initialized cor…
Organizer
NeurIPS 2022
Account · 963 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Contributed Papers: Panel 1
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Online Matching with Advice: Tight Robustness-Consistency Tradeoffs for the Two-Stage Model
Watch later
Billy Jin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
DiSC: Differential Spectral Clustering of Features
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Set-based Meta-Interpolation for Few-Task Meta-Learning
Watch later
Seanie Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
Watch later
Zhijing Jin, …
Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%