Zobrazeno 1 - 10
of 1 404
pro vyhledávání: '"A, Werman"'
Autor:
Bleiberg, Yair, Werman, Michael
Coordinate-based Multi-Layer Perceptrons (MLPs) are known to have difficulty reconstructing high frequencies of the training data. A common solution to this problem is Positional Encoding (PE), which has become quite popular. However, PE has drawback
Externí odkaz:
http://arxiv.org/abs/2411.05052
This paper presents a novel technique for camera calibration using a single view that incorporates a spherical mirror. Leveraging the distinct characteristics of the sphere's contour visible in the image and its reflections, we showcase the effective
Externí odkaz:
http://arxiv.org/abs/2409.16386
Autor:
Arad, Yoav, Werman, Michael
Video Anomaly Detection (VAD) plays a crucial role in modern surveillance systems, aiming to identify various anomalies in real-world situations. However, current benchmark datasets predominantly emphasize simple, single-frame anomalies such as novel
Externí odkaz:
http://arxiv.org/abs/2310.01904
Autor:
Kolpakov, Alexander, Werman, Michael
Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds. The algorithm is based on minimizing the Frobenius distance between two elements of the Grassmannian. For this purpose, an indefinite
Externí odkaz:
http://arxiv.org/abs/2303.02698
Autor:
Kolpakov, Alexander, Werman, Michael
In this note, we propose an approach to initialize the Iterative Closest Point (ICP) algorithm to match unlabelled point clouds related by rigid transformations. The method is based on matching the ellipsoids defined by the points' covariance matrice
Externí odkaz:
http://arxiv.org/abs/2212.05332
Autor:
Kurihana, Takuya, Foster, Ian, Willett, Rebecca, Jenkins, Sydney, Koenig, Kathryn, Werman, Ruby, Lourenco, Ricardo Barros, Neo, Casper, Moyer, Elisabeth
We present a framework for cloud characterization that leverages modern unsupervised deep learning technologies. While previous neural network-based cloud classification models have used supervised learning methods, unsupervised learning allows us to
Externí odkaz:
http://arxiv.org/abs/2209.15585
Publikováno v:
AppliedMath, Vol 4, Iss 2, Pp 561-569 (2024)
This paper presents a novel deep-learning network designed to detect intervals of jump discontinuities in single-variable piecewise smooth functions from their noisy samples. Enhancing the accuracy of jump discontinuity estimations can be used to fin
Externí odkaz:
https://doaj.org/article/0b0f45feb61f4bba98face1ec36ac3c0
Autor:
Gottlieb, Noam, Werman, Michael
Deep neural networks (DNNs) and decision trees (DTs) are both state-of-the-art classifiers. DNNs perform well due to their representational learning capabilities, while DTs are computationally efficient as they perform inference along one route (root
Externí odkaz:
http://arxiv.org/abs/2207.01127
Autor:
Damelin, Steven B., Werman, Michael
We study the best approximation problem: \[ \displaystyle \min_{\alpha\in \mathbb R^m}\max_{1\leq i\leq n}\left|y_i -\sum_{j=1}^m \alpha_j \Gamma_j ({\bf x}_i) \right|. \] Here: $\Gamma:=\left\{\Gamma_1,...,\Gamma_m\right\}$ is a list of functions wh
Externí odkaz:
http://arxiv.org/abs/2204.07949
Autor:
Soloveitchik, Michael, Werman, Michael
We introduce a fully convolutional fractional scaling component, FCFS. Fully convolutional networks can be applied to any size input and previously did not support non-integer scaling. Our architecture is simple with an efficient single layer impleme
Externí odkaz:
http://arxiv.org/abs/2203.10670