arXiv subjects

Yosi Keller

Publications and source records attributed to Yosi Keller.

33 records · Page 2Linked to original sources

arXiv2022

FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment

We present Face Swapping GAN (FSGAN) for face swapping and reenactment. Unlike previous work, we offer a subject agnostic swapping scheme that can be applied to pairs of faces without requiring training on those faces. We derive a novel iterative deep learning--based approach for face reenactment which adjusts significant pose and expression variations that can be applied to a single image or a video sequence. For video sequences, we introduce a continuous interpolation of the face views based on reenactment, Delaunay Triangulation, and barycentric coordinates. Occluded face regions are handled by a face completion network. Finally, we use a face blending network for seamless blending of the two faces while preserving the target skin color and lighting conditions. This network uses a novel Poisson blending loss combining Poisson optimization with a perceptual loss. We compare our approach to existing state-of-the-art systems and show our results to be both qualitatively and quantitatively superior. This work describes extensions of the FSGAN method, proposed in an earlier conference version of our work, as well as additional experiments and results.

cs.CV↗

arXiv2021

Learning Multi-Scene Absolute Pose Regression with Transformers

Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron head is trained with images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended for learning multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent features and scenes encoding into candidate pose predictions. This mechanism allows our model to focus on general features that are informative for localization while embedding multiple scenes in parallel. We evaluate our method on commonly benchmarked indoor and outdoor datasets and show that it surpasses both multi-scene and state-of-the-art single-scene absolute pose regressors. We make our code publicly available from https://github.com/yolish/multi-scene-pose-transformer.

cs.CV↗

arXiv2021

Facial Landmarks Localization using Cascaded Neural Networks

The accurate localization of facial landmarks is at the core of face analysis tasks, such as face recognition and facial expression analysis, to name a few. In this work, we propose a novel localization approach based on a deep learning architecture that utilizes cascaded subnetworks with convolutional neural network units. The cascaded units of the first subnetwork estimate heatmap-based encodings of the landmarks locations, while the cascaded units of the second subnetwork receive as input the output of the corresponding heatmap estimation units, and refine them through regression. The proposed scheme is experimentally shown to compare favorably with contemporary state-of-the-art schemes, especially when applied to images depicting challenging localization conditions.

cs.CV↗

arXiv2021

Joint detection and matching of feature points in multimodal images

In this work, we propose a novel Convolutional Neural Network (CNN) architecture for the joint detection and matching of feature points in images acquired by different sensors using a single forward pass. The resulting feature detector is tightly coupled with the feature descriptor, in contrast to classical approaches (SIFT, etc.), where the detection phase precedes and differs from computing the descriptor. Our approach utilizes two CNN subnetworks, the first being a Siamese CNN and the second, consisting of dual non-weight-sharing CNNs. This allows simultaneous processing and fusion of the joint and disjoint cues in the multimodal image patches. The proposed approach is experimentally shown to outperform contemporary state-of-the-art schemes when applied to multiple datasets of multimodal images. It is also shown to provide repeatable feature points detections across multisensor images, outperforming state-of-the-art detectors. To the best of our knowledge, it is the first unified approach for the detection and matching of such images.

cs.CV↗

arXiv2021

Paying Attention to Activation Maps in Camera Pose Regression

Camera pose regression methods apply a single forward pass to the query image to estimate the camera pose. As such, they offer a fast and light-weight alternative to traditional localization schemes based on image retrieval. Pose regression approaches simultaneously learn two regression tasks, aiming to jointly estimate the camera position and orientation using a single embedding vector computed by a convolutional backbone. We propose an attention-based approach for pose regression, where the convolutional activation maps are used as sequential inputs. Transformers are applied to encode the sequential activation maps as latent vectors, used for camera pose regression. This allows us to pay attention to spatially-varying deep features. Using two Transformer heads, we separately focus on the features for camera position and orientation, based on how informative they are per task. Our proposed approach is shown to compare favorably to contemporary pose regressors schemes and achieves state-of-the-art accuracy across multiple outdoor and indoor benchmarks. In particular, to the best of our knowledge, our approach is the only method to attain sub-meter average accuracy across outdoor scenes. We make our code publicly available from here.

cs.CV↗

arXiv2020

A Unified Approach to Kinship Verification

In this work, we propose a deep learning-based approach for kin verification using a unified multi-task learning scheme where all kinship classes are jointly learned. This allows us to better utilize small training sets that are typical of kin verification. We introduce a novel approach for fusing the embeddings of kin images, to avoid overfitting, which is a common issue in training such networks. An adaptive sampling scheme is derived for the training set images to resolve the inherent imbalance in kin verification datasets. A thorough ablation study exemplifies the effectivity of our approach, which is experimentally shown to outperform contemporary state-of-the-art kin verification results when applied to the Families In the Wild, FG2018, and FG2020 datasets.

cs.CV↗

arXiv2020

DeepFake Detection Based on the Discrepancy Between the Face and its Context

We propose a method for detecting face swapping and other identity manipulations in single images. Face swapping methods, such as DeepFake, manipulate the face region, aiming to adjust the face to the appearance of its context, while leaving the context unchanged. We show that this modus operandi produces discrepancies between the two regions. These discrepancies offer exploitable telltale signs of manipulation. Our approach involves two networks: (i) a face identification network that considers the face region bounded by a tight semantic segmentation, and (ii) a context recognition network that considers the face context (e.g., hair, ears, neck). We describe a method which uses the recognition signals from our two networks to detect such discrepancies, providing a complementary detection signal that improves conventional real vs. fake classifiers commonly used for detecting fake images. Our method achieves state of the art results on the FaceForensics++, Celeb-DF-v2, and DFDC benchmarks for face manipulation detection, and even generalizes to detect fakes produced by unseen methods.

cs.CV↗

arXiv2020

Auto-ML Deep Learning for Rashi Scripts OCR

In this work we propose an OCR scheme for manuscripts printed in Rashi font that is an ancient Hebrew font and corresponding dialect used in religious Jewish literature, for more than 600 years. The proposed scheme utilizes a convolution neural network (CNN) for visual inference and Long-Short Term Memory (LSTM) to learn the Rashi scripts dialect. In particular, we derive an AutoML scheme to optimize the CNN architecture, and a book-specific CNN training to improve the OCR accuracy. The proposed scheme achieved an accuracy of more than 99.8% using a dataset of more than 3M annotated letters from the Responsa Project dataset.

cs.CV↗

arXiv2019

FSGAN: Subject Agnostic Face Swapping and Reenactment

We present Face Swapping GAN (FSGAN) for face swapping and reenactment. Unlike previous work, FSGAN is subject agnostic and can be applied to pairs of faces without requiring training on those faces. To this end, we describe a number of technical contributions. We derive a novel recurrent neural network (RNN)-based approach for face reenactment which adjusts for both pose and expression variations and can be applied to a single image or a video sequence. For video sequences, we introduce continuous interpolation of the face views based on reenactment, Delaunay Triangulation, and barycentric coordinates. Occluded face regions are handled by a face completion network. Finally, we use a face blending network for seamless blending of the two faces while preserving target skin color and lighting conditions. This network uses a novel Poisson blending loss which combines Poisson optimization with perceptual loss. We compare our approach to existing state-of-the-art systems and show our results to be both qualitatively and quantitatively superior.

cs.CV↗

arXiv2019

Multi-scale Processing of Noisy Images using Edge Preservation Losses

Noisy images processing is a fundamental task of computer vision. The first example is the detection of faint edges in noisy images, a challenging problem studied in the last decades. A recent study introduced a fast method to detect faint edges in the highest accuracy among all the existing approaches. Their complexity is nearly linear in the image's pixels and their runtime is seconds for a noisy image. Their approach utilizes a multi-scale binary partitioning of the image. By utilizing the multi-scale U-net architecture, we show in this paper that their method can be dramatically improved in both aspects of run time and accuracy. By training the network on a dataset of binary images, we developed an approach for faint edge detection that works in a linear complexity. Our runtime of a noisy image is milliseconds on a GPU. Even though our method is orders of magnitude faster, we still achieve higher accuracy of detection under many challenging scenarios. In addition, we show that our approach to performing multi-scale preprocessing of noisy images using U-net improves the ability to perform other vision tasks under the presence of noise. We prove it on the problems of noisy objects classification and classical image denoising. We show that multi-scale denoising can be carried out by a novel edge preservation loss. As our experiments show, we achieve high-quality results in the three aspects of faint edge detection, noisy image classification and natural image denoising.

cs.CV↗

arXiv2018

SelfKin: Self Adjusted Deep Model For Kinship Verification

One of the unsolved challenges in the field of biometrics and face recognition is Kinship Verification. This problem aims to understand if two people are family-related and how (sisters, brothers, etc.) Solving this problem can give rise to varied tasks and applications. In the area of homeland security (HLS) it is crucial to auto-detect if the person questioned is related to a wanted suspect, In the field of biometrics, kinship-verification can help to discriminate between families by photos and in the field of predicting or fashion it can help to predict an older or younger model of people faces. Lately, and with the advanced deep learning technology, this problem has gained focus from the research community in matters of data and research. In this article, we propose using a Deep Learning approach for solving the Kinship-Verification problem. Further, we offer a novel self-learning deep model, which learns the essential features from different faces. We show that our model wins the Recognize Families In the Wild(RFIW2018,FG2018) challenge and obtains state-of-the-art results. Moreover, we show that our proposed model can reduce the size of the network by half without loss in performance.

cs.CV↗

arXiv2018

Registration and Fusion of Multi-Spectral Images Using a Novel Edge Descriptor

In this paper we introduce a fully end-to-end approach for multi-spectral image registration and fusion. Our method for fusion combines images from different spectral channels into a single fused image by different approaches for low and high frequency signals. A prerequisite of fusion is a stage of geometric alignment between the spectral bands, commonly referred to as registration. Unfortunately, common methods for image registration of a single spectral channel do not yield reasonable results on images from different modalities. For that end, we introduce a new algorithm for multi-spectral image registration, based on a novel edge descriptor of feature points. Our method achieves an accurate alignment of a level that allows us to further fuse the images. As our experiments show, we produce a high quality of multi-spectral image registration and fusion under many challenging scenarios.

cs.CV↗

arXiv2018

Deep Multi-Spectral Registration Using Invariant Descriptor Learning

In this paper, we introduce a novel deep-learning method to align cross-spectral images. Our approach relies on a learned descriptor which is invariant to different spectra. Multi-modal images of the same scene capture different signals and therefore their registration is challenging and it is not solved by classic approaches. To that end, we developed a feature-based approach that solves the visible (VIS) to Near-Infra-Red (NIR) registration problem. Our algorithm detects corners by Harris and matches them by a patch-metric learned on top of CIFAR-10 network descriptor. As our experiments demonstrate we achieve a high-quality alignment of cross-spectral images with a sub-pixel accuracy. Comparing to other existing methods, our approach is more accurate in the task of VIS to NIR registration.

cs.CV↗

arXiv2017

Financial Time Series Prediction Using Deep Learning

In this work we present a data-driven end-to-end Deep Learning approach for time series prediction, applied to financial time series. A Deep Learning scheme is derived to predict the temporal trends of stocks and ETFs in NYSE or NASDAQ. Our approach is based on a neural network (NN) that is applied to raw financial data inputs, and is trained to predict the temporal trends of stocks and ETFs. In order to handle commission-based trading, we derive an investment strategy that utilizes the probabilistic outputs of the NN, and optimizes the average return. The proposed scheme is shown to provide statistically significant accurate predictions of financial market trends, and the investment strategy is shown to be profitable under this challenging setup. The performance compares favorably with contemporary benchmarks along two-years of back-testing.

eess.SP↗

arXiv2014

An algorithm for improving Non-Local Means operators via low-rank approximation

We present a method for improving a Non Local Means operator by computing its low-rank approximation. The low-rank operator is constructed by applying a filter to the spectrum of the original Non Local Means operator. This results in an operator which is less sensitive to noise while preserving important properties of the original operator. The method is efficiently implemented based on Chebyshev polynomials and is demonstrated on the application of natural images denoising. For this application, we provide a comprehensive comparison of our method with leading denoising methods.

cs.CV↗