Unsupervised deep multi-shape matching
Abstract 3D shape matching is a long-standing problem in computer vision and computer
graphics. While deep neural networks were shown to lead to state-of-the-art results in shape …
graphics. While deep neural networks were shown to lead to state-of-the-art results in shape …
Near-optimal performance bounds for orthogonal and permutation group synchronization via spectral methods
S Ling - Applied and Computational Harmonic Analysis, 2022 - Elsevier
Group synchronization asks to recover group elements from their pairwise measurements. It
has found numerous applications across various scientific disciplines. In this work, we focus …
has found numerous applications across various scientific disciplines. In this work, we focus …
Quantum motion segmentation
Motion segmentation is a challenging problem that seeks to identify independent motions in
two or several input images. This paper introduces the first algorithm for motion …
two or several input images. This paper introduces the first algorithm for motion …
Iterative algorithm for discrete structure recovery
C Gao, AY Zhang - The Annals of Statistics, 2022 - projecteuclid.org
The supplement [46] includes a few more examples and all the technical proofs. We first
analyze approximate ranking in Appendix A. Z/k Z synchronization and permutation …
analyze approximate ranking in Appendix A. Z/k Z synchronization and permutation …
Improved performance guarantees for orthogonal group synchronization via generalized power method
S Ling - SIAM Journal on Optimization, 2022 - SIAM
Given the noisy pairwise measurements among a set of unknown group elements, how does
one recover them efficiently and robustly? This problem, known as group synchronization …
one recover them efficiently and robustly? This problem, known as group synchronization …
Robust group synchronization via cycle-edge message passing
We propose a general framework for solving the group synchronization problem, where we
focus on the setting of adversarial or uniform corruption and sufficiently small noise …
focus on the setting of adversarial or uniform corruption and sufficiently small noise …
Robust group synchronization via quadratic programming
We propose a novel quadratic programming formulation for estimating the corruption levels
in group synchronization, and use these estimates to solve this problem. Our objective …
in group synchronization, and use these estimates to solve this problem. Our objective …
Correspondence attention transformer: A context-sensitive network for two-view correspondence learning
Seeking reliable correspondences then recovering camera poses from a set of putative
correspondences extracted from two images of the same scene is a fundamental problem in …
correspondences extracted from two images of the same scene is a fundamental problem in …
Multi-frame motion segmentation by combining two-frame results
In this paper we consider the motion segmentation problem on sparse and unstructured
datasets involving rigid motions, motivated by multibody structure from motion. In particular …
datasets involving rigid motions, motivated by multibody structure from motion. In particular …
Fast, accurate and memory-efficient partial permutation synchronization
Previous partial permutation synchronization (PPS) algorithms, which are commonly used
for multi-object matching, often involve computation-intensive and memory-demanding …
for multi-object matching, often involve computation-intensive and memory-demanding …