papers

Publications (44)

cs.LG2026

When Is Compositional Reasoning Learnable from Verifiable Rewards?

Daniel Barzilai, Yotam Wolf, Ronen Basri

The emergence of compositional reasoning in large language models through reinforcement learning with verifiable rewards (RLVR) has been a key driver of recent empirical successes.…

cs.CV2020

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Lior Yariv, Yoni Kasten, Dror Moran +4

In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry,…

cs.CV2015

Fast Detection of Curved Edges at Low SNR

Nati Ofir, Meirav Galun, Boaz Nadler +1

Detecting edges is a fundamental problem in computer vision with many applications, some involving very noisy images. While most edge detection methods are fast, they perform well…

cs.CV2015

Elasticity-based Matching by Minimizing the Symmetric Difference of Shapes

Konrad Simon, Ronen Basri

We consider the problem of matching two shapes assuming these shapes are related by an elastic deformation. Using linearized elasticity theory and the finite element method we seek…

cs.CV2016

Learning 3D Deformation of Animals from 2D Images

Angjoo Kanazawa, Shahar Kovalsky, Ronen Basri +1

Understanding how an animal can deform and articulate is essential for a realistic modification of its 3D model. In this paper, we show that such information can be learned from us…

cs.CV2019

Resultant Based Incremental Recovery of Camera Pose from Pairwise Matches

Yoni Kasten, Meirav Galun, Ronen Basri

Incremental (online) structure from motion pipelines seek to recover the camera matrix associated with an image given images, , whose camera matrices h…

cs.CV2021

Segmenting Microcalcifications in Mammograms and its Applications

Roee Zamir, Shai Bagon, David Samocha +3

Microcalcifications are small deposits of calcium that appear in mammograms as bright white specks on the soft tissue background of the breast. Microcalcifications may be a unique…

cs.CV2024

Consensus Learning with Deep Sets for Essential Matrix Estimation

Dror Moran, Yuval Margalit, Guy Trostianetsky +3

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…

cs.CG2015

A Hyperelastic Two-Scale Optimization Model for Shape Matching

Konrad Simon, Sameer Sheorey, David Jacobs +1

We suggest a novel shape matching algorithm for three-dimensional surface meshes of disk or sphere topology. The method is based on the physical theory of nonlinear elasticity and…

cs.NE2016

Efficient Representation of Low-Dimensional Manifolds using Deep Networks

Ronen Basri, David Jacobs

We consider the ability of deep neural networks to represent data that lies near a low-dimensional manifold in a high-dimensional space. We show that deep networks can efficiently…

cs.LG2020

Frequency Bias in Neural Networks for Input of Non-Uniform Density

Ronen Basri, Meirav Galun, Amnon Geifman +3

Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from…

cs.CV2024

CinePile: A Long Video Question Answering Dataset and Benchmark

Ruchit Rawal, Khalid Saifullah, Miquel Farré +4

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 succes…

cs.CV2026

GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations

Fadi Khatib, Dror Moran, Guy Trostianetsky +3

GSVisLoc is a visual localization technique that estimates a camera's position and orientation by matching features from a 3D Gaussian Splatting scene model to features extracted f…

#visual localization#3d gaussian splatting#scene representation#camera pose estimation
cs.LG2024

Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum

Amnon Geifman, Daniel Barzilai, Ronen Basri +1

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 i…

cs.CV2015

A Global Approach for Solving Edge-Matching Puzzles

Shahar Z. Kovalsky, Daniel Glasner, Ronen Basri

We consider apictorial edge-matching puzzles, in which the goal is to arrange a collection of puzzle pieces with colored edges so that the colors match along the edges of adjacent…

cs.CV2015

Wide baseline stereo matching with convex bounded-distortion constraints

Meirav Galun, Tal Amir, Tal Hassner +2

Finding correspondences in wide baseline setups is a challenging problem. Existing approaches have focused largely on developing better feature descriptors for correspondence and o…

cs.CV2017

On Detection of Faint Edges in Noisy Images

Nati Ofir, Meirav Galun, Sharon Alpert +3

A fundamental question for edge detection in noisy images is how faint can an edge be and still be detected. In this paper we offer a formalism to study this question and subsequen…

cs.LG2019

The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies

Ronen Basri, David Jacobs, Yoni Kasten +1

We study the relationship between the frequency of a function and the speed at which a neural network learns it. We build on recent results that show that the dynamics of overparam…

cs.LG2022

On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels

Amnon Geifman, Meirav Galun, David Jacobs +1

We study the properties of various over-parametrized convolutional neural architectures through their respective Gaussian process and neural tangent kernels. We prove that, with no…

cs.LG2021

Shift Invariance Can Reduce Adversarial Robustness

Songwei Ge, Vasu Singla, Ronen Basri +1

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 sensitivit…

cs.CV2020

Algebraic Characterization of Essential Matrices and Their Averaging in Multiview Settings

Yoni Kasten, Amnon Geifman, Meirav Galun +1

Essential matrix averaging, i.e., the task of recovering camera locations and orientations in calibrated, multiview settings, is a first step in global approaches to Euclidean stru…

cs.LG2020

Learning Algebraic Multigrid Using Graph Neural Networks

Ilay Luz, Meirav Galun, Haggai Maron +2

Efficient numerical solvers for sparse linear systems are crucial in science and engineering. One of the fastest methods for solving large-scale sparse linear systems is algebraic…

cs.CV2017

Solving Uncalibrated Photometric Stereo Using Fewer Images by Jointly Optimizing Low-rank Matrix Completion and Integrability

Soumyadip Sengupta, Hao Zhou, Walter Forkel +3

We introduce a new, integrated approach to uncalibrated photometric stereo. We perform 3D reconstruction of Lambertian objects using multiple images produced by unknown, directiona…

cs.LG2020

On the Similarity between the Laplace and Neural Tangent Kernels

Amnon Geifman, Abhay Yadav, Yoni Kasten +3

Recent theoretical work has shown that massively overparameterized neural networks are equivalent to kernel regressors that use Neural Tangent Kernels(NTK). Experiments show that t…

cs.CV2017

Photometric Stereo by Hemispherical Metric Embedding

Ofer Bartal, Nati Ofir, Yaron Lipman +1

Photometric Stereo methods seek to reconstruct the 3d shape of an object from motionless images obtained with varying illumination. Most existing methods solve a restricted problem…

cs.CV2014

From Shading to Local Shape

Ying Xiong, Ayan Chakrabarti, Ronen Basri +3

We develop a framework for extracting a concise representation of the shape information available from diffuse shading in a small image patch. This produces a mid-level scene descr…

cs.CV2017

A New Rank Constraint on Multi-view Fundamental Matrices, and its Application to Camera Location Recovery

Soumyadip Sengupta, Tal Amir, Meirav Galun +4

Accurate estimation of camera matrices is an important step in structure from motion algorithms. In this paper we introduce a novel rank constraint on collections of fundamental ma…

cs.LG2021

The Trimmed Lasso: Sparse Recovery Guarantees and Practical Optimization by the Generalized Soft-Min Penalty

Tal Amir, Ronen Basri, Boaz Nadler

We present a new approach to solve the sparse approximation or best subset selection problem, namely find a -sparse vector that minimizes the r…

cs.CV2020

Averaging Essential and Fundamental Matrices in Collinear Camera Settings

Amnon Geifman, Yoni Kasten, Meirav Galun +1

Global methods to Structure from Motion have gained popularity in recent years. A significant drawback of global methods is their sensitivity to collinear camera settings. In this…

cs.CV2021

GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matrices

Yoni Kasten, Amnon Geifman, Meirav Galun +1

This paper addresses the problem of recovering projective camera matrices from collections of fundamental matrices in multiview settings. We make two main contributions. First, giv…

cs.CV2015

Stable Camera Motion Estimation Using Convex Programming

Onur Ozyesil, Amit Singer, Ronen Basri

We study the inverse problem of estimating n locations (up to global scale, translation and negation) in from noisy measurements of a subset of the (unsigned)…

cs.CV2021

Deep Permutation Equivariant Structure from Motion

Dror Moran, Hodaya Koslowsky, Yoni Kasten +3

Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Neverthe…

cs.CV2017

A Survey of Structure from Motion

Onur Ozyesil, Vladislav Voroninski, Ronen Basri +1

The structure from motion (SfM) problem in computer vision is the problem of recovering the three-dimensional (D) structure of a stationary scene from a set of projective measur…

cs.LG2021

Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks

Yuval Belfer, Amnon Geifman, Meirav Galun +1

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…

math.OC2015

Identification of Structured LTI MIMO State-Space Models

Chengpu Yu, Michel Verhaegen, Shahar Kovalsky +1

The identification of structured state-space model has been intensively studied for a long time but still has not been adequately addressed. The main challenge is that the involved…

cs.LG2026

Identifying and Evaluating Inactive Heads in Pretrained LLMs

Pedro Sandoval-Segura, Xijun Wang, Ashwinee Panda +4

Attention is foundational to large language models (LLMs), enabling different heads to have diverse focus on relevant input tokens. However, learned behaviors like attention sinks,…

cs.LG2025

Querying Kernel Methods Suffices for Reconstructing their Training Data

Daniel Barzilai, Yuval Margalit, Eitan Gronich +3

Over-parameterized models have raised concerns about their potential to memorize training data, even when achieving strong generalization. The privacy implications of such memoriza…

cs.CV2024

Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression

Fadi Khatib, Yuval Margalit, Meirav Galun +1

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 differe…

cs.LG2025

Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps

Henry Li, Ronen Basri, Yuval Kluger

Cascaded models are multi-scale generative models with a marked capacity for producing perceptually impressive samples at high resolutions. In this work, we show that they can also…

cs.CV2013

Single View Depth Estimation from Examples

Tal Hassner, Ronen Basri

We describe a non-parametric, "example-based" method for estimating the depth of an object, viewed in a single photo. Our method consults a database of example 3D geometries, searc…

cs.CV2025

RESfM: Robust Deep Equivariant Structure from Motion

Fadi Khatib, Yoni Kasten, Dror Moran +2

Multiview Structure from Motion is a fundamental and challenging computer vision problem. A recent deep-based approach utilized matrix equivariant architectures for simultaneous re…

cs.LG2023

A Kernel Perspective of Skip Connections in Convolutional Networks

Daniel Barzilai, Amnon Geifman, Meirav Galun +1

Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing. Here we study their properties through their…

stat.ML2018

SpectralNet: Spectral Clustering using Deep Neural Networks

Uri Shaham, Kelly Stanton, Henry Li +3

Spectral clustering is a leading and popular technique in unsupervised data analysis. Two of its major limitations are scalability and generalization of the spectral embedding (i.e…

math.NA2019

Learning to Optimize Multigrid PDE Solvers

Daniel Greenfeld, Meirav Galun, Ron Kimmel +2

Constructing fast numerical solvers for partial differential equations (PDEs) is crucial for many scientific disciplines. A leading technique for solving large-scale PDEs is using…