arXiv subjects

Karen Egiazarian

Publications and source records attributed to Karen Egiazarian.

At least 19 recordsLinked to original sources

arXiv2026

FU-Mamba: A Frequency-Enhanced Dynamic Scanning Framework for Oralscan Image Segmentation

Oralscan image segmentation is essential for computer-aided diagnosis and treatment planning in digital dentistry. However, existing visual state space models (SSMs) often rely on manually designed scanning orders to flatten image patches into sequences, which disrupts the semantic spatial continuity and hinders coherent feature extraction from key foreground regions. Moreover, elements such as inconsistent lighting, reflective surfaces, and noise during data acquisition disrupt the frequency distribution by diminishing high-frequency details while enhancing low-frequency components, consequently hindering the accurate localization of boundaries. In response to these challenges, we introduce FU-Mamba, an innovative framework that incorporates dynamic scanning and frequency domain enhancement within the SSM architecture. Specifically, the Dynamic Mamba Block (DMB) adaptively learns sampling offsets via a trainable offset prediction network and performs flexible bilinear interpolation, enabling content-aware scanning that preserves spatial coherence. Furthermore, a frequency domain enhancement block balances spectral components through wavelet-guided decomposition and spectrum pooling, improving robustness under adverse imaging conditions. Experimental findings indicate that FU-Mamba attains a notable enhancement in segmentation accuracy, evidenced by a 1.1% increase in the mean intersection over union (mIoU) metric when evaluated on the dental segmentation dataset. Project page: https://byte2bite.github.io/FU-Mamba/

cs.CV↗

arXiv2026

SVGS: Single-View to 3D Object Editing via Gaussian Splatting

Text-driven 3D scene editing has attracted considerable interest due to its convenience and user-friendliness. However, methods that rely on implicit 3D representations, such as Neural Radiance Fields (NeRF), while effective in rendering complex scenes, are hindered by slow processing speeds and limited control over specific regions of the scene. Moreover, existing approaches, including Instruct-NeRF2NeRF and GaussianEditor, which utilize multi-view editing strategies, frequently produce inconsistent results across different views when executing text instructions. This inconsistency can adversely affect the overall performance of the model, complicating the task of balancing the consistency of editing results with editing efficiency. To address these challenges, we propose a novel method termed Single-View to 3D Object Editing via Gaussian Splatting (SVGS), which is a single-view text-driven editing technique based on 3D Gaussian Splatting (3DGS). Specifically, in response to text instructions, we introduce a single-view editing strategy grounded in multi-view diffusion models, which reconstructs 3D scenes by leveraging only those views that yield consistent editing results. Additionally, we employ sparse 3D Gaussian Splatting as the 3D representation, which significantly enhances editing efficiency. We conducted a comparative analysis of SVGS against existing baseline methods across various scene settings, and the results indicate that SVGS outperforms its counterparts in both editing capability and processing speed, representing a significant advancement in 3D editing technology. For further details, please visit our project page at: https://amateurc.github.io/svgs.github.io.

cs.CV↗

arXiv2026

DM-CFO: A Diffusion Model for Compositional 3D Tooth Generation with Collision-Free Optimization

The automatic design of a 3D tooth model plays a crucial role in dental digitization. However, current approaches face challenges in compositional 3D tooth generation because both the layouts and shapes of missing teeth need to be optimized.In addition, collision conflicts are often omitted in 3D Gaussian-based compositional 3D generation, where objects may intersect with each other due to the absence of explicit geometric information on the object surfaces. Motivated by graph generation through diffusion models and collision detection using 3D Gaussians, we propose an approach named DM-CFO for compositional tooth generation, where the layout of missing teeth is progressively restored during the denoising phase under both text and graph constraints. Then, the Gaussian parameters of each layout-guided tooth and the entire jaw are alternately updated using score distillation sampling (SDS). Furthermore, a regularization term based on the distances between the 3D Gaussians of neighboring teeth and the anchor tooth is introduced to penalize tooth intersections. Experimental results on three tooth-design datasets demonstrate that our approach significantly improves the multiview consistency and realism of the generated teeth compared with existing methods. Project page: https://amateurc.github.io/CF-3DTeeth/.

cs.CV↗

arXiv2024

Towards Realistic Landmark-Guided Facial Video Inpainting Based on GANs

Facial video inpainting plays a crucial role in a wide range of applications, including but not limited to the removal of obstructions in video conferencing and telemedicine, enhancement of facial expression analysis, privacy protection, integration of graphical overlays, and virtual makeup. This domain presents serious challenges due to the intricate nature of facial features and the inherent human familiarity with faces, heightening the need for accurate and persuasive completions. In addressing challenges specifically related to occlusion removal in this context, our focus is on the progressive task of generating complete images from facial data covered by masks, ensuring both spatial and temporal coherence. Our study introduces a network designed for expression-based video inpainting, employing generative adversarial networks (GANs) to handle static and moving occlusions across all frames. By utilizing facial landmarks and an occlusion-free reference image, our model maintains the user's identity consistently across frames. We further enhance emotional preservation through a customized facial expression recognition (FER) loss function, ensuring detailed inpainted outputs. Our proposed framework exhibits proficiency in eliminating occlusions from facial videos in an adaptive form, whether appearing static or dynamic on the frames, while providing realistic and coherent results.

cs.CV↗

arXiv2024

Expression-aware video inpainting for HMD removal in XR applications

Head-mounted displays (HMDs) serve as indispensable devices for observing extended reality (XR) environments and virtual content. However, HMDs present an obstacle to external recording techniques as they block the upper face of the user. This limitation significantly affects social XR applications, specifically teleconferencing, where facial features and eye gaze information play a vital role in creating an immersive user experience. In this study, we propose a new network for expression-aware video inpainting for HMD removal (EVI-HRnet) based on generative adversarial networks (GANs). Our model effectively fills in missing information with regard to facial landmarks and a single occlusion-free reference image of the user. The framework and its components ensure the preservation of the user's identity across frames using the reference frame. To further improve the level of realism of the inpainted output, we introduce a novel facial expression recognition (FER) loss function for emotion preservation. Our results demonstrate the remarkable capability of the proposed framework to remove HMDs from facial videos while maintaining the subject's facial expression and identity. Moreover, the outputs exhibit temporal consistency along the inpainted frames. This lightweight framework presents a practical approach for HMD occlusion removal, with the potential to enhance various collaborative XR applications without the need for additional hardware.

cs.CV↗

arXiv2023

An Overview of Advances in Signal Processing Techniques for Classical and Quantum Wideband Synthetic Apertures

Rapid developments in synthetic aperture (SA) systems, which generate a larger aperture with greater angular resolution than is inherently possible from the physical dimensions of a single sensor alone, are leading to novel research avenues in several signal processing applications. The SAs may either use a mechanical positioner to move an antenna through space or deploy a distributed network of sensors. With the advent of new hardware technologies, the SAs tend to be denser nowadays. The recent opening of higher frequency bands has led to wide SA bandwidths. In general, new techniques and setups are required to harness the potential of wide SAs in space and bandwidth. Herein, we provide a brief overview of emerging signal processing trends in such spatially and spectrally wideband SA systems. This guide is intended to aid newcomers in navigating the most critical issues in SA analysis and further supports the development of new theories in the field. In particular, we cover the theoretical framework and practical underpinnings of wideband SA radar, channel sounding, sonar, radiometry, and optical applications. Apart from the classical SA applications, we also discuss the quantum electric-field-sensing probes in SAs that are currently undergoing active research but remain at nascent stages of development.

eess.SP↗

arXiv2022

Unfolding-Aided Bootstrapped Phase Retrieval in Optical Imaging

Phase retrieval in optical imaging refers to the recovery of a complex signal from phaseless data acquired in the form of its diffraction patterns. These patterns are acquired through a system with a coherent light source that employs a diffractive optical element (DOE) to modulate the scene resulting in coded diffraction patterns at the sensor. Recently, the hybrid approach of model-driven network or deep unfolding has emerged as an effective alternative to conventional model-based and learning-based phase retrieval techniques because it allows for bounding the complexity of algorithms while also retaining their efficacy. Additionally, such hybrid approaches have shown promise in improving the design of DOEs that follow theoretical uniqueness conditions. There are opportunities to exploit novel experimental setups and resolve even more complex DOE phase retrieval applications. This paper presents an overview of algorithms and applications of deep unfolding for bootstrapped - regardless of near, middle, and far zones - phase retrieval.

physics.optics↗

arXiv2022

Residual Swin Transformer Channel Attention Network for Image Demosaicing

Image demosaicing is problem of interpolating full- resolution color images from raw sensor (color filter array) data. During last decade, deep neural networks have been widely used in image restoration, and in particular, in demosaicing, attaining significant performance improvement. In recent years, vision transformers have been designed and successfully used in various computer vision applications. One of the recent methods of image restoration based on a Swin Transformer (ST), SwinIR, demonstrates state-of-the-art performance with a smaller number of parameters than neural network-based methods. Inspired by the success of SwinIR, we propose in this paper a novel Swin Transformer-based network for image demosaicing, called RSTCANet. To extract image features, RSTCANet stacks several residual Swin Transformer Channel Attention blocks (RSTCAB), introducing the channel attention for each two successive ST blocks. Extensive experiments demonstrate that RSTCANet out- performs state-of-the-art image demosaicing methods, and has a smaller number of parameters.

cs.CV↗

arXiv2022

On design of hybrid diffractive optics for achromatic extended depth-of-field (EDoF) RGB imaging

A hybrid imaging system is a simultaneous physical arrangement of a refractive lens and a multilevel phase mask (MPM) as a diffractive optical element (DOE). The favorable properties of the hybrid setup are improved extended-depth-of-field (EDoF) imaging and low chromatic aberrations. We built a fully differentiable image formation model in order to use neural network techniques to optimize imaging. At the first stage, the design framework relies on the model-based approach with numerical simulation and end-to-end joint optimization of both MPM and imaging algorithms. In the second stage, MPM is fixed as found at the first stage, and the image processing is optimized experimentally using the CNN learning-based approach with MPM implemented by a spatial light modulator. The paper is concentrated on a comparative analysis of imaging accuracy and quality for design with various basic optical parameters: aperture size, lens focal length, and distance between MPM and sensor. We point out that the varying aperture size, lens focal length, and distance between MPM and sensor are for the first time considered for end-to-end optimization of EDoF. We numerically and experimentally compare the designs for visible wavelength interval [400-700]nm and the following EDoF ranges: [0.5-100]m for simulations and [0.5-1.9]m for experimental tests. This study concerns an application of hybrid optics for compact cameras with aperture [5-9] mm and distance between MPM and sensor [3-10]mm.

physics.optics↗

arXiv2021

Learning-based Noise Component Map Estimation for Image Denoising

A problem of image denoising when images are corrupted by a non-stationary noise is considered in this paper. Since in practice no a priori information on noise is available, noise statistics should be pre-estimated for image denoising. In this paper, deep convolutional neural network (CNN) based method for estimation of a map of local, patch-wise, standard deviations of noise (so-called sigma-map) is proposed. It achieves the state-of-the-art performance in accuracy of estimation of sigma-map for the case of non-stationary noise, as well as estimation of noise variance for the case of additive white Gaussian noise. Extensive experiments on image denoising using estimated sigma-maps demonstrate that our method outperforms recent CNN-based blind image denoising methods by up to 6 dB in PSNR, as well as other state-of-the-art methods based on sigma-map estimation by up to 0.5 dB, providing same time better usage flexibility. Comparison with the ideal case, when denoising is applied using ground-truth sigma-map, shows that a difference of corresponding PSNR values for most of noise levels is within 0.1-0.2 dB and does not exceeds 0.6 dB.

eess.IV↗

arXiv2021

SSR-PR: Single-shot Super-Resolution Phase Retrieval based two prior calibration tests

We propose a novel approach and algorithm based on two preliminary tests of the optical system elements to enhance the super-resolved complex-valued imaging. The approach is developed for inverse phase imaging in a single-shot lensless optical setup. Imaging is based on wavefront modulation by a single binary phase mask. The preliminary tests compensate errors in the optical system and correct a carrying wavefront, reducing the gap between real-life experiments and computational modeling, which improve imaging significantly both qualitatively and quantitatively. These two tests are performed for observation of the laser beam and phase mask along, and might be considered as a preliminary system calibration. The corrected carrying wavefront is embedded into the proposed iterative Single-shot Super-Resolution Phase Retrieval (SSR-PR) algorithm. Improved initial diffraction pattern upsampling, and a combination of sparse and deep learning based filters achieves the super-resolved reconstructions. Simulations and physical experiments demonstrate the high-quality super-resolution phase imaging. In the simulations, we showed that the SSR-PR algorithm corrects the errors of the proposed optical system and reconstructs phase details 4x smaller than the sensor pixel size. In physical experiment 2um thick lines of USAF phase-target were resolved, which is almost 2x smaller than the sensor pixel size and corresponds to the smallest resolvable group of used test target. For phase bio-imaging, we provide Buccal Epithelial Cells reconstructed in computational super-resolution and the quality was of the same level as a digital holographic system with 40x magnification objective. Furthermore, the single-shot advantage provides the possibility to record dynamic scenes, where the framerate is limited only by the used camera. We provide amplitude-phase video clip of a moving alive single-celled eukaryote.

physics.optics↗

arXiv2021

Power-Balanced Hybrid Optics Boosted Design for Achromatic Extended-Depth-of-Field Imaging via Optimized Mixed OTF

The power-balanced hybrid optical imaging system is a special design of a diffractive computational camera, introduced in this paper, with image formation by a refractive lens and Multilevel Phase Mask (MPM). This system provides a long focal depth with low chromatic aberrations thanks to MPM and a high energy light concentration due to the refractive lens. We introduce the concept of optical power balance between the lens and MPM which controls the contribution of each element to modulate the incoming light. Additional unique features of our MPM design are the inclusion of quantization of the MPM's shape on the number of levels and the Fresnel order (thickness) using a smoothing function. To optimize optical power-balance as well as the MPM, we build a fully-differentiable image formation model for joint optimization of optical and imaging parameters for the proposed camera using Neural Network techniques. Additionally, we optimize a single Wiener-like optical transfer function (OTF) invariant to depth to reconstruct a sharp image. We numerically and experimentally compare the designed system with its counterparts, lensless and just-lens optical systems, for the visible wavelength interval (400-700)nm and the depth-of-field range (0.5-$\infty$m for numerical and 0.5-2m for experimental). The attained results demonstrate that the proposed system equipped with the optimal OTF overcomes its counterparts (even when they are used with optimized OTF) in terms of reconstruction quality for off-focus distances. The simulation results also reveal that optimizing the optical power-balance, Fresnel order, and the number of levels parameters are essential for system performance attaining an improvement of up to 5dB of PSNR using the optimized OTF compared with its counterpart lensless setup.

physics.optics↗

arXiv2021

ADMM and Spectral Proximity Operators in Hyperspectral Broadband Phase Retrieval for Quantitative Phase Imaging

A novel formulation of the hyperspectral broadband phase retrieval is developed for the scenario where both object and modulation phase masks are spectrally varying. The proposed algorithm is based on a complex domain version of the alternating direction method of multipliers (ADMM) and Spectral Proximity Operators (SPO) derived for Gaussian and Poissonian observations. Computations for these operators are reduced to the solution of sets of cubic (for Gaussian) and quadratic (for Poissonian) algebraic equations. These proximity operators resolve two problems. Firstly, the complex domain spectral components of signals are extracted from the total intensity observations calculated as sums of the signal spectral intensities. In this way, the spectral analysis of the total intensities is achieved. Secondly, the noisy observations are filtered, compromising noisy intensity observations and their predicted counterparts. The ability to resolve the hyperspectral broadband phase retrieval problem and to find the spectrum varying object are essentially defined by the spectral properties of object and image formation operators. The simulation tests demonstrate that the phase retrieval in this formulation can be successfully resolved.

eess.IV↗

arXiv2020

Flashlight CNN Image Denoising

This paper proposes a learning-based denoising method called FlashLight CNN (FLCNN) that implements a deep neural network for image denoising. The proposed approach is based on deep residual networks and inception networks and it is able to leverage many more parameters than residual networks alone for denoising grayscale images corrupted by additive white Gaussian noise (AWGN). FlashLight CNN demonstrates state of the art performance when compared quantitatively and visually with the current state of the art image denoising methods.

eess.IV↗

arXiv2020

Lensless hyperspectral imaging by Fourier transform spectroscopy for broadband visible light: phase retrieval technique

A novel phase retrieval algorithm for broadband hyperspectral phase imaging from noisy intensity observations is proposed. It utilizes advantages of the Fourier Transform spectroscopy in the self-referencing optical setup and provides, additionally beyond spectral intensity distribution, reconstruction of the investigated object's phase. The noise amplification Fellgett's disadvantage is relaxed by the application of sparse wavefront noise filtering embedded in the proposed algorithm. The algorithm reliability is proved by simulation tests and results of physical experiments on transparent objects which demonstrate precise phase imaging and object depth (profile) reconstructions.

eess.IV↗

arXiv2019

The Practicality of Stochastic Optimization in Imaging Inverse Problems

In this work we investigate the practicality of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging inverse problems. Such algorithms have been shown in the machine learning literature to have optimal complexities in theory, and provide great improvement empirically over the deterministic gradient methods. Surprisingly, in some tasks such as image deblurring, many of such methods fail to converge faster than the accelerated deterministic gradient methods, even in terms of epoch counts. We investigate this phenomenon and propose a theory-inspired mechanism for the practitioners to efficiently characterize whether it is beneficial for an inverse problem to be solved by stochastic optimization techniques or not. Using standard tools in numerical linear algebra, we derive conditions on the spectral structure of the inverse problem for being a suitable application of stochastic gradient methods. Particularly, we show that, for an imaging inverse problem, if and only if its Hessain matrix has a fast-decaying eigenspectrum, then the stochastic gradient methods can be more advantageous than deterministic methods for solving such a problem. Our results also provide guidance on choosing appropriately the partition minibatch schemes, showing that a good minibatch scheme typically has relatively low correlation within each of the minibatches. Finally, we propose an accelerated primal-dual SGD algorithm in order to tackle another key bottleneck of stochastic optimization which is the heavy computation of proximal operators. The proposed method has fast convergence rate in practice, and is able to efficiently handle non-smooth regularization terms which are coupled with linear operators.

math.OC↗

arXiv2019

Hyperspectral holography and spectroscopy: computational features of inverse discrete cosine transform

Broadband hyperspectral digital holography and Fourier transform spectroscopy are important instruments in various science and application fields. In the digital hyperspectral holography and spectroscopy the variable of interest are obtained as inverse discrete cosine transforms of observed diffractive intensity patterns. In these notes, we provide a variety of algorithms for the inverse cosine transform with the proofs of perfect spectrum reconstruction, as well as we discuss and illustrate some nontrivial features of these algorithms.

math.NA↗

arXiv2019

Hyperspectral phase imaging based on denoising in complex-valued eigensubspace

A new denoising algorithm for hyperspectral complex domain data has been developed and studied. This algorithm is based on the complex domain block-matching 3D filter including the 3D Wiener filtering stage. The developed algorithm is applied and tuned to work in the singular value decomposition (SVD) eigenspace of reduced dimension. The accuracy and quantitative advantage of the new algorithm are demonstrated in simulation tests and in the processing of the experimental data. It is shown that the algorithm is effective and provides reliable results even for highly noisy data.

eess.IV↗