Search Results for author:
Found 49 papers, 28 papers with code
Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior
Neural Radiance Fields (NeRF) have advanced photorealistic novel view synthesis, but their reliance on photometric reconstruction introduces artifacts, commonly known as "floaters".
Sifting through the haystack -- efficiently finding rare animal behaviors in large-scale datasets
Our method consistently outperformed traditional random sampling, offering an average improvement of 70% in performance and creating datasets even when the behavior of interest was only 0. 02% of the data.
Memories of Forgotten Concepts
Diffusion models dominate the space of text-to-image generation, yet they may produce undesirable outputs, including explicit content or private data.
Edge Weight Prediction For Category-Agnostic Pose Estimation
Category-Agnostic Pose Estimation (CAPE) localizes keypoints across diverse object categories with a single model, using one or a few annotated support images.
Ranked #3 on
2D Pose Estimation
on MP-100
CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation
We validate our novel approach using the MP-100 benchmark, a comprehensive dataset spanning over 100 categories and 18, 000 images.
Ranked #2 on
2D Pose Estimation
on MP-100
VF-NeRF: Viewshed Fields for Rigid NeRF Registration
3D scene registration is a fundamental problem in computer vision that seeks the best 6-DoF alignment between two scenes.
Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
We formulate the problem by finding the roots of an implicit equation and devlop a method to solve it efficiently.
Optimize and Reduce: A Top-Down Approach for Image Vectorization
Vector image representation is a popular choice when editability and flexibility in resolution are desired.
A Graph-Based Approach for Category-Agnostic Pose Estimation
Traditional 2D pose estimation models are limited by their category-specific design, making them suitable only for predefined object categories.
Ranked #4 on
2D Pose Estimation
on MP-100
Securing Neural Networks with Knapsack Optimization
In this paper, we focus on ResNets, which serve as the backbone for many Computer Vision tasks, and we aim to reduce their non-linear components, specifically, the number of ReLUs.
Prior based Sampling for Adaptive LiDAR
We propose SampleDepth, a Convolutional Neural Network (CNN), that is suited for an adaptive LiDAR.
Taming Normalizing Flows
We propose an algorithm for taming Normalizing Flow models - changing the probability that the model will produce a specific image or image category.
SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow
Scene flow estimation is a long-standing problem in computer vision, where the goal is to find the 3D motion of a scene from its consecutive observations.
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes
In this setting, an adversarial input mesh deceives the autoencoder by forcing it to reconstruct a different geometric shape at its output.
Normalizing Flows for Human Pose Anomaly Detection
Video anomaly detection is an ill-posed problem because it relies on many parameters such as appearance, pose, camera angle, background, and more.
Ranked #1 on
Anomaly Detection
on UBnormal
(using extra training data)
Abnormal Event Detection In Video
Anomaly Detection In Surveillance Videos
+3
Aggregating Layers for Deepfake Detection
Crucially, most work in this domain assume that the Deepfakes in the test set come from the same Deepfake algorithms that were used for training the network.
Stress-Testing Point Cloud Registration on Automotive LiDAR
Rigid Point Cloud Registration (PCR) algorithms aim to estimate the 6-DOF relative motion between two point clouds, which is important in various fields, including autonomous driving.
How Low Can We Go? Pixel Annotation for Semantic Segmentation
Based on this single-image-annotation experiment, we design an experiment to quickly annotate an entire data set.
Transformaly -- Two (Feature Spaces) Are Better Than One
Anomaly detection is a well-established research area that seeks to identify samples outside of a predetermined distribution.
Ranked #2 on
Anomaly Detection
on One-class CIFAR-100
(using extra training data)
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Model
In our experiments, we examined the transferability of our adversarial mask to a wide range of FR model architectures and datasets.
DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
We present a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction.
Ranked #5 on
3D Dense Shape Correspondence
on SHREC'19
DeepBBS: Deep Best Buddies for Point Cloud Registration
The Best Buddies criterion is a strong indication for correct matches that, in turn, leads to accurate registration.
kNet: A Deep kNN Network To Handle Label Noise
To use kNet, we first train a preliminary network on the data set, and then train kNet on the penultimate layer of the preliminary network. We find that kNet gives a smooth approximation of kNN, and cannot handle the sharp label changes between samples that kNN can exhibit.
Reducing ReLU Count for Privacy-Preserving CNN Speedup
Experiments on several datasets reveal that we can cut the number of ReLU operations by up to three orders of magnitude and, as a result, cut the communication bandwidth by more than 50%.
Geometric Adversarial Attacks and Defenses on 3D Point Clouds
Additionally, we demonstrate the robustness of our attack in the case of defense, where we show that remnant characteristics of the target shape are still present at the output after applying the defense to the adversarial input.
Rethinking FUN: Frequency-Domain Utilization Networks
The search for efficient neural network architectures has gained much focus in recent years, where modern architectures focus not only on accuracy but also on inference time and model size.
Best Buddies Registration for Point Clouds
We propose new, and robust, loss functions for the point cloud registration problem.
Co-occurrence Based Texture Synthesis
As image generation techniques mature, there is a growing interest in explainable representations that are easy to understand and intuitive to manipulate.
Proximity Preserving Binary Code using Signed Graph-Cut
We show that the proposed approximation is superior to the commonly used spectral methods with respect to both accuracy and complexity.
Deep Image Compression using Decoder Side Information
We base our algorithm on the assumption that the image available to the encoder and the image available to the decoder are correlated, and we let the network learn these correlations in the training phase.
Graph Embedded Pose Clustering for Anomaly Detection
We propose a new method for anomaly detection of human actions.
Ranked #7 on
Video Anomaly Detection
on HR-UBnormal
SampleNet: Differentiable Point Cloud Sampling
As the size of the point cloud grows, so do the computational demands of these tasks.
Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation
The field of self-supervised monocular depth estimation has seen huge advancements in recent years.
Ranked #62 on
Monocular Depth Estimation
on KITTI Eigen split
CrowdCam: Dynamic Region Segmentation
We consider the problem of segmenting dynamic regions in CrowdCam images, where a dynamic region is the projection of a moving 3D object on the image plane.
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset
The attenuation depends both on the water body and the 3D structure of the scene, making color restoration difficult.
Matching Pixels Using Co-Occurrence Statistics
We propose a new error measure for matching pixels that is based on co-occurrence statistics.
The Resistance to Label Noise in K-NN and DNN Depends on its Concentration
We investigate the classification performance of K-nearest neighbors (K-NN) and deep neural networks (DNNs) in the presence of label noise.
Co-occurrence Filter
It is based on the Bilateral Filter (BF) but instead of using a Gaussian on the range values to preserve edges it relies on a co-occurrence matrix.
Detecting Moving Regions in CrowdCam Images
We address the novel problem of detecting dynamic regions in CrowdCam images, a set of still images captured by a group of people.
Best-Buddies Tracking
BBS was introduced as a similarity measure between two point sets and was shown to be very effective for template matching.
Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors
We propose a novel method for template matching in unconstrained environments.
Non-Local Image Dehazing
This dependency is expressed in the transmission coefficients, that control the scene attenuation and amount of haze in every pixel.
Peeking Template Matching for Depth Extension
We demonstrate on real-world data that our algorithm is capable of completing a full 3D scene from a single depth image and can synthesize a full depth map from a novel viewpoint of the scene.
Spatially Coherent Random Forests
Each tree in the forest produces a segmentation of the image plane and the boundaries of the segmentations of all trees are aggregated to produce a final hierarchical contour map.
Best-Buddies Similarity for Robust Template Matching
We propose a novel method for template matching in unconstrained environments.
Inverting RANSAC: Global Model Detection via Inlier Rate Estimation
This work presents a novel approach for detecting inliers in a given set of correspondences (matches).
Stereo on a budget
Instead of having both cameras send their entire image to the host computer, the left camera sends its image to the host while the right camera sends only a fraction $\epsilon$ of its image.
FasT-Match: Fast Affine Template Matching
Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure.
