Search Results for author: Vitomir Štruc

Found 38 papers, 11 papers with code

EFaR 2023: Efficient Face Recognition Competition

1 code implementation8 Aug 2023 Jan Niklas Kolf, Fadi Boutros, Jurek Elliesen, Markus Theuerkauf, Naser Damer, Mohamad Alansari, Oussama Abdul Hay, Sara Alansari, Sajid Javed, Naoufel Werghi, Klemen Grm, Vitomir Štruc, Fernando Alonso-Fernandez, Kevin Hernandez Diaz, Josef Bigun, Anjith George, Christophe Ecabert, Hatef Otroshi Shahreza, Ketan Kotwal, Sébastien Marcel, Iurii Medvedev, Bo Jin, Diogo Nunes, Ahmad Hassanpour, Pankaj Khatiwada, Aafan Ahmad Toor, Bian Yang

To drive further development of efficient face recognition models, the submitted solutions are ranked based on a weighted score of the achieved verification accuracies on a diverse set of benchmarks, as well as the deployability given by the number of floating-point operations and model size.

Lightweight Face Recognition Quantization

On the Vulnerability of DeepFake Detectors to Attacks Generated by Denoising Diffusion Models

no code implementations11 Jul 2023 Marija Ivanovska, Vitomir Štruc

The detection of malicious deepfakes is a constantly evolving problem that requires continuous monitoring of detectors to ensure they can detect image manipulations generated by the latest emerging models.

Denoising Face Reenactment +1

Face Morphing Attack Detection with Denoising Diffusion Probabilistic Models

1 code implementation International Workshop on Biometrics and Forensics (IWBF) 2023 Marija Ivanovska, Vitomir Štruc

Existing MAD techniques predominantly rely on discriminative models that learn from examples of bona fide and morphed images and, as a result, often exhibit sub-optimal generalization performance when confronted with unknown types of morphing attacks.

Denoising Face Morphing Attack Detection +1

Beyond Detection: Visual Realism Assessment of Deepfakes

no code implementations9 Jun 2023 Luka Dragar, Peter Peer, Vitomir Štruc, Borut Batagelj

In the era of rapid digitalization and artificial intelligence advancements, the development of DeepFake technology has posed significant security and privacy concerns.

Face Swapping

Optimization-Based Improvement of Face Image Quality Assessment Techniques

1 code implementation24 May 2023 Žiga Babnik, Naser Damer, Vitomir Štruc

To help improve the performance and stability of FR systems in such unconstrained settings, face image quality assessment (FIQA) techniques try to infer sample-quality information from the input face images that can aid with the recognition process.

Face Image Quality Face Image Quality Assessment +1

DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models

1 code implementation9 May 2023 Žiga Babnik, Peter Peer, Vitomir Štruc

In this paper, we present a powerful new FIQA approach, named DifFIQA, which relies on denoising diffusion probabilistic models (DDPM) and ensures highly competitive results.

Denoising Face Image Quality +2

FICE: Text-Conditioned Fashion Image Editing With Guided GAN Inversion

1 code implementation5 Jan 2023 Martin Pernuš, Clinton Fookes, Vitomir Štruc, Simon Dobrišek

We address these constraints by proposing a novel text-conditioned editing model, called FICE (Fashion Image CLIP Editing), capable of handling a wide variety of diverse text descriptions to guide the editing procedure.

Attribute Virtual Try-on

Body Segmentation Using Multi-task Learning

no code implementations13 Dec 2022 Julijan Jug, Ajda Lampe, Vitomir Štruc, Peter Peer

Body segmentation is an important step in many computer vision problems involving human images and one of the key components that affects the performance of all downstream tasks.

Multi-Task Learning Pose Prediction +1

C-VTON: Context-Driven Image-Based Virtual Try-On Network

2 code implementations8 Dec 2022 Benjamin Fele, Ajda Lampe, Peter Peer, Vitomir Štruc

At the core of the C-VTON pipeline are: (i) a geometric matching procedure that efficiently aligns the target clothing with the pose of the person in the input images, and (ii) a powerful image generator that utilizes various types of contextual information when synthesizing the final try-on result.

Geometric Matching Virtual Try-on

FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration

1 code implementation5 Dec 2022 Žiga Babnik, Peter Peer, Vitomir Štruc

In this paper, we propose a novel approach to face image quality assessment, called FaceQAN, that is based on adversarial examples and relies on the analysis of adversarial noise which can be calculated with any FR model learned by using some form of gradient descent.

Face Image Quality Face Image Quality Assessment +1

Assessing Bias in Face Image Quality Assessment

no code implementations28 Nov 2022 Žiga Babnik, Vitomir Štruc

Although modern face recognition systems are known to perform well, several studies have found that such systems often exhibit problems with demographic bias.

Face Image Quality Face Image Quality Assessment +1

Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition

no code implementations28 Nov 2022 Klemen Grm, Berk Kemal Özata, Vitomir Štruc, Hazim Kemal Ekenel

In this paper, we aim to address the large domain gap between high-resolution face images, e. g., from professional portrait photography, and low-quality surveillance images, e. g., from security cameras.

Face Identification Face Recognition +1

PrivacyProber: Assessment and Detection of Soft-Biometric Privacy-Enhancing Techniques

no code implementations16 Nov 2022 Peter Rot, Peter Peer, Vitomir Štruc

Soft-biometric privacy-enhancing techniques represent machine learning methods that aim to: (i) mitigate privacy concerns associated with face recognition technology by suppressing selected soft-biometric attributes in facial images (e. g., gender, age, ethnicity) and (ii) make unsolicited extraction of sensitive personal information infeasible.

Attribute Face Recognition

GlassesGAN: Eyewear Personalization using Synthetic Appearance Discovery and Targeted Subspace Modeling

no code implementations CVPR 2023 Richard Plesh, Peter Peer, Vitomir Štruc

To facilitate the editing process with GlassesGAN, we propose a Targeted Subspace Modelling (TSM) procedure that, based on a novel mechanism for (synthetic) appearance discovery in the latent space of a pre-trained GAN generator, constructs an eyeglasses-specific (latent) subspace that the editing framework can utilize.

Hierarchical Superquadric Decomposition with Implicit Space Separation

no code implementations15 Sep 2022 Jaka Šircelj, Peter Peer, Franc Solina, Vitomir Štruc

We introduce a new method to reconstruct 3D objects using a set of volumetric primitives, i. e., superquadrics.


Iterative Optimization of Pseudo Ground-Truth Face Image Quality Labels

no code implementations31 Aug 2022 Žiga Babnik, Vitomir Štruc

At ten iterations, the approach seems to perform the best, consistently outperforming the base quality scores of the three FIQA methods, chosen for the experiments.

Face Image Quality Face Image Quality Assessment +1

Face Morphing Attack Detection Using Privacy-Aware Training Data

no code implementations2 Jul 2022 Marija Ivanovska, Andrej Kronovšek, Peter Peer, Vitomir Štruc, Borut Batagelj

Images of morphed faces pose a serious threat to face recognition--based security systems, as they can be used to illegally verify the identity of multiple people with a single morphed image.

Face Morphing Attack Detection Face Recognition

BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images

1 code implementation3 May 2022 Darian Tomašević, Peter Peer, Vitomir Štruc

Current state-of-the-art segmentation techniques for ocular images are critically dependent on large-scale annotated datasets, which are labor-intensive to gather and often raise privacy concerns.

Image Generation Segmentation

A Global Modeling Approach for Load Forecasting in Distribution Networks

no code implementations1 Apr 2022 Miha Grabner, Yi Wang, Qingsong Wen, Boštjan Blažič, Vitomir Štruc

Efficient load forecasting is needed to ensure better observability in the distribution networks, whereas such forecasting is made possible by an increasing number of smart meter installations.

Load Forecasting

An Attack on Facial Soft-biometric Privacy Enhancement

no code implementations24 Nov 2021 Dailé Osorio-Roig, Christian Rathgeb, Pawel Drozdowski, Philipp Terhörst, Vitomir Štruc, Christoph Busch

Future works on privacy-enhancing face recognition are encouraged to include the proposed attack in evaluations on the privacy protection.

Attribute Dimensionality Reduction +1

Y-GAN: Learning Dual Data Representations for Efficient Anomaly Detection

no code implementations28 Sep 2021 Marija Ivanovska, Vitomir Štruc

Due to the separation of semantically-relevant and residual information, Y-GAN is able to derive informative data representations that allow for efficient anomaly detection across a diverse set of anomaly detection tasks.

Anomaly Detection Disentanglement

High Resolution Face Editing with Masked GAN Latent Code Optimization

2 code implementations20 Mar 2021 Martin Pernuš, Vitomir Štruc, Simon Dobrišek

The proposed approach is based on an optimization procedure that directly optimizes the latent code of a pre-trained (state-of-the-art) Generative Adversarial Network (i. e., StyleGAN2) with respect to several constraints that ensure: (i) preservation of relevant image content, (ii) generation of the targeted facial attributes, and (iii) spatially--selective treatment of local image areas.

Attribute Face Parsing +2

Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks

no code implementations28 Jan 2020 Jaka Šircelj, Tim Oblak, Klemen Grm, Uroš Petković, Aleš Jaklič, Peter Peer, Vitomir Štruc, Franc Solina

In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives.

Simultaneous regression and feature learning for facial landmarking

no code implementations24 Apr 2019 Janez Križaj, Peter Peer, Vitomir Štruc, Simon Dobrišek

We develop two distinct approaches around the proposed gating mechanism: i) the first uses a gated multiple ridge descent (GRID) mechanism in conjunction with established (hand-crafted) HOG features for face alignment and achieves state-of-the-art landmarking performance across a wide range of facial poses, ii) the second simultaneously learns multiple-descent directions as well as binary features (SMUF) that are optimal for the alignment tasks and in addition to competitive landmarking results also ensures extremely rapid processing.

Attribute Face Alignment +1

Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study

no code implementations13 Apr 2019 Tim Oblak, Klemen Grm, Aleš Jaklič, Peter Peer, Vitomir Štruc, Franc Solina

It has been a longstanding goal in computer vision to describe the 3D physical space in terms of parameterized volumetric models that would allow autonomous machines to understand and interact with their surroundings.

The Unconstrained Ear Recognition Challenge 2019 - ArXiv Version With Appendix

no code implementations11 Mar 2019 Žiga Emeršič, Aruna Kumar S. V., B. S. Harish, Weronika Gutfeter, Jalil Nourmohammadi Khiarak, Andrzej Pacut, Earnest Hansley, Mauricio Pamplona Segundo, Sudeep Sarkar, Hyeonjung Park, Gi Pyo Nam, Ig-Jae Kim, Sagar G. Sangodkar, Ümit Kaçar, Murvet Kirci, Li Yuan, Jishou Yuan, Haonan Zhao, Fei Lu, Junying Mao, Xiaoshuang Zhang, Dogucan Yaman, Fevziye Irem Eyiokur, Kadir Bulut Özler, Hazim Kemal Ekenel, Debbrota Paul Chowdhury, Sambit Bakshi, Pankaj K. Sa, Banshidhar Majhi, Peter Peer, Vitomir Štruc

The goal of the challenge is to assess the performance of existing ear recognition techniques on a challenging large-scale ear dataset and to analyze performance of the technology from various viewpoints, such as generalization abilities to unseen data characteristics, sensitivity to rotations, occlusions and image resolution and performance bias on sub-groups of subjects, selected based on demographic criteria, i. e. gender and ethnicity.

Benchmarking Person Recognition

Face Hallucination Revisited: An Exploratory Study on Dataset Bias

no code implementations21 Dec 2018 Klemen Grm, Martin Pernuš, Leo Cluzel, Walter Scheirer, Simon Dobrišek, Vitomir Štruc

This down-sampling (or degradation) procedure not only defines the characteristics of the LR training data, but also determines the type of image degradations the learned FH models are eventually able to handle.

Face Hallucination Hallucination

Face hallucination using cascaded super-resolution and identity priors

no code implementations28 May 2018 Klemen Grm, Simon Dobrišek, Walter J. Scheirer, Vitomir Štruc

In this paper we address the problem of hallucinating high-resolution facial images from unaligned low-resolution inputs at high magnification factors.

Face Hallucination Face Recognition +2

Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild

no code implementations27 Nov 2017 Žiga Emeršič, Dejan Štepec, Vitomir Štruc, Peter Peer

The result of our work is the first CNN-based approach to ear recognition that is also made publicly available to the research community.

Data Augmentation

Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations

1 code implementation4 Oct 2017 Klemen Grm, Vitomir Štruc, Anais Artiges, Matthieu Caron, Hazim Kemal Ekenel

However, studies systematically exploring the strengths and weaknesses of existing deep models for face recognition are still relatively scarce in the literature.

Face Recognition Face Verification

The Unconstrained Ear Recognition Challenge

no code implementations23 Aug 2017 Žiga Emeršič, Dejan Štepec, Vitomir Štruc, Peter Peer, Anjith George, Adil Ahmad, Elshibani Omar, Terrance E. Boult, Reza Safdari, Yuxiang Zhou, Stefanos Zafeiriou, Dogucan Yaman, Fevziye I. Eyiokur, Hazim K. Ekenel

In this paper we present the results of the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem of person recognition from ear images captured in uncontrolled conditions.

Benchmarking Person Recognition

Face Deidentification with Generative Deep Neural Networks

no code implementations28 Jul 2017 Blaž Meden, Refik Can Malli, Sebastjan Fabijan, Hazim Kemal Ekenel, Vitomir Štruc, Peter Peer

Our results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is highly effective.

Pixel-wise Ear Detection with Convolutional Encoder-Decoder Networks

no code implementations1 Feb 2017 Žiga Emeršič, Luka Lan Gabriel, Vitomir Štruc, Peter Peer

For our technique, we formulate the problem of ear detection as a two-class segmentation problem and train a convolutional encoder-decoder network based on the SegNet architecture to distinguish between image-pixels belonging to either the ear or the non-ear class.

object-detection Object Detection +1

Ear Recognition: More Than a Survey

no code implementations18 Nov 2016 Žiga Emeršič, Vitomir Štruc, Peter Peer

This paper presents an overview of the field of automatic ear recognition (from 2D images) and focuses specifically on the most recent, descriptor-based methods proposed in this area.

Cannot find the paper you are looking for? You can Submit a new open access paper.