Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Li, Shaohan"'
Group synchronization plays a crucial role in global pipelines for Structure from Motion (SfM). Its formulation is nonconvex and it is faced with highly corrupted measurements. Cycle consistency has been effective in addressing these challenges. Howe
Externí odkaz:
http://arxiv.org/abs/2407.04260
We investigate the training and generalization errors of overparameterized neural networks (NNs) with a wide class of leaky rectified linear unit (ReLU) functions. More specifically, we carefully upper bound both the convergence rate of the training
Externí odkaz:
http://arxiv.org/abs/2402.11942
Previous partial permutation synchronization (PPS) algorithms, which are commonly used for multi-object matching, often involve computation-intensive and memory-demanding matrix operations. These operations become intractable for large scale structur
Externí odkaz:
http://arxiv.org/abs/2203.16505
Publikováno v:
Proceedings of the 2021 International Conference on 3D Vision (3DV), 2021, pp. 352-360
We develop new statistics for robustly filtering corrupted keypoint matches in the structure from motion pipeline. The statistics are based on consistency constraints that arise within the clustered structure of the graph of keypoint matches. The sta
Externí odkaz:
http://arxiv.org/abs/2201.04797
Publikováno v:
Advances in Neural Information Processing Systems (NeurIPS) 33, 15243--15253 (2020)
We propose an efficient and robust iterative solution to the multi-object matching problem. We first clarify serious limitations of current methods as well as the inappropriateness of the standard iteratively reweighted least squares procedure. In vi
Externí odkaz:
http://arxiv.org/abs/2006.06658