Zobrazeno 1 - 10
of 232
pro vyhledávání: '"Basri, Ronen"'
Robust estimation of the essential matrix, which encodes the relative position and orientation of two cameras, is a fundamental step in structure from motion pipelines. Recent deep-based methods achieved accurate estimation by using complex network a
Externí odkaz:
http://arxiv.org/abs/2406.17414
Autor:
Rawal, Ruchit, Saifullah, Khalid, Farré, Miquel, Basri, Ronen, Jacobs, David, Somepalli, Gowthami, Goldstein, Tom
Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames from a vid
Externí odkaz:
http://arxiv.org/abs/2405.08813
Multiview Structure from Motion is a fundamental and challenging computer vision problem. A recent deep-based approach was proposed utilizing matrix equivariant architectures for the simultaneous recovery of camera pose and 3D scene structure from la
Externí odkaz:
http://arxiv.org/abs/2404.14280
Wide neural networks are biased towards learning certain functions, influencing both the rate of convergence of gradient descent (GD) and the functions that are reachable with GD in finite training time. As such, there is a great need for methods tha
Externí odkaz:
http://arxiv.org/abs/2307.14531
Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing. Here we study their properties through their Gaussian Process and Neural Tangent kernels. We derive explicit formu
Externí odkaz:
http://arxiv.org/abs/2211.14810
This paper proposes a generalizable, end-to-end deep learning-based method for relative pose regression between two images. Given two images of the same scene captured from different viewpoints, our method predicts the relative rotation and translati
Externí odkaz:
http://arxiv.org/abs/2211.14950
We study the properties of various over-parametrized convolutional neural architectures through their respective Gaussian process and neural tangent kernels. We prove that, with normalized multi-channel input and ReLU activation, the eigenfunctions o
Externí odkaz:
http://arxiv.org/abs/2203.09255
Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses and 3D sc
Externí odkaz:
http://arxiv.org/abs/2104.06703
Deep residual network architectures have been shown to achieve superior accuracy over classical feed-forward networks, yet their success is still not fully understood. Focusing on massively over-parameterized, fully connected residual networks with R
Externí odkaz:
http://arxiv.org/abs/2104.03093
Shift invariance is a critical property of CNNs that improves performance on classification. However, we show that invariance to circular shifts can also lead to greater sensitivity to adversarial attacks. We first characterize the margin between cla
Externí odkaz:
http://arxiv.org/abs/2103.02695