Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction
Shape Non-rigid Kinematics (SNK) introduces a novel zero-shot method for non-rigid shape matching that eliminates the need for extensive training or ground truth data, combining axiomatic and learning-based approaches while addressing their limitations.
Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction
Shape Non-rigid Kinematics (SNK) introduces a zero-shot method for non-rigid shape matching without the need for extensive training data, demonstrating competitive results on traditional benchmarks.
Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction
Shape Non-rigid Kinematics (SNK) introduces a zero-shot method for non-rigid shape matching without the need for extensive training data.
Unsupervised Non-Rigid Point Cloud Shape Correspondence via Equivariant Local Reference Frames and Refinement
The core message of this work is to address the challenges of exponential complexity and out-of-distribution geometric contexts in unsupervised non-rigid point cloud shape correspondence by learning pair-wise independent SE(3)-equivariant Local Reference Frames (LRFs) and refining them to adapt to specific contexts.
© 2024 by Linnk AI