Related papers: Faceting for direction-dependent spectral deconvol…

Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks. This paper proposes to decompose the…

In this work, we introduce DifFoundMAD, a parameter-efficient D-MAD framework that exploits the generalisation capabilities of vision foundation models (FM) to capture discrepancies between suspected morphs and live capture images. In…

Face sketch to digital image matching is an important challenge of face recognition that involves matching across different domains. Current research efforts have primarily focused on extracting domain invariant representations or learning…

Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detection methods to forgery-irrelevant features and…

Synthesis imaging in radio astronomy is affected by instrumental and atmospheric effects which introduce direction-dependent (DD) gains.The antenna power pattern varies both as a function of time and frequency. The broad band time varying…

Recently, Deep Convolution Networks (DCNNs) have been applied to the task of face alignment and have shown potential for learning improved feature representations. Although deeper layers can capture abstract concepts like pose, it is…

This paper presents a multi-pose face recognition approach using hybrid face features descriptors (HFFD). The HFFD is a face descriptor containing of rich discriminant information that is created by fusing some frequency-based features…

In the domain of Biometrics, recognition systems based on iris, fingerprint or palm print scans etc. are often considered more dependable due to extremely low variance in the properties of these entities with respect to time. However, over…

We present a filtering technique that can be applied to individual baselines of wide-bandwidth, wide-field interferometric data to geometrically select regions on the celestial sphere that contain primary calibration sources. The technique…

Microscopy imaging is vital in biology research and diagnosis. When imaging at the scale of cell or molecule level, mechanical drift on the axial axis can be difficult to correct. Although multi-scale networks have been developed for…

Waveform design for joint communication and sensing (JCAS) is an important research direction, focusing on providing an optimal tradeoff between communication and sensing performance. In this paper, we first describe the conventional…

Existing deep learning based facial landmark detection methods have achieved excellent performance. These methods, however, do not explicitly embed the structural dependencies among landmark points. They hence cannot preserve the geometric…

Wavefront aberrations can reflect the imaging quality of high-performance optical systems better than geometric aberrations. Although laser interferometers have emerged as the main tool for measurement of transmitted wavefronts, their…

In radio astronomy obtaining a high dynamic range in synthesis imaging of wide fields requires a correction for time and direction-dependent effects. Applying direction-dependent correction can be done by either partitioning the image in…

With the rising popularity of virtual worlds, the importance of data-driven parametric models of 3D meshes has grown rapidly. Numerous applications, such as computer vision, procedural generation, and mesh editing, vastly rely on these…

We introduce the Fast Holographic Deconvolution method for analyzing interferometric radio data. Our new method is an extension of A-projection/software-holography/forward modeling analysis techniques and shares their precision…

Face recognition under extreme head poses is a challenging task. Ideally, a face recognition system should perform well across different head poses, which is known as pose-invariant face recognition. To achieve pose invariance, current…

Recently, deep-learning-based approaches have been widely studied for deformable image registration task. However, most efforts directly map the composite image representation to spatial transformation through the convolutional neural…

We introduce a new technique for imaging the polarized radio sky using interferometric data. The new approach, which we call Faraday synthesis, combines aperture and rotation measure synthesis imaging and deconvolution into a single…

High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields. The spatial information in these images reflects the object's texture features, while the spectral information…