Related papers: Evaluating Registration Without Ground Truth

Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and…

Most existing face image Super-Resolution (SR) methods assume that the Low-Resolution (LR) images were artificially downsampled from High-Resolution (HR) images with bicubic interpolation. This operation changes the natural image…

Lacking realistic ground truth data, image denoising techniques are traditionally evaluated on images corrupted by synthesized i.i.d. Gaussian noise. We aim to obviate this unrealistic setting by developing a methodology for benchmarking…

Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space.…

Topics generated by topic models are usually represented by lists of $t$ terms or alternatively using short phrases and images. The current state-of-the-art work on labeling topics using images selects images by re-ranking a small set of…

We propose a novel method for large-scale image stitching that is robust against repetitive patterns and featureless regions in the imagery. In such cases, state-of-the-art image stitching methods easily produce image alignment artifacts,…

The overwhelming popularity of social media has resulted in bulk amounts of personal photos being uploaded to the internet every day. Since these photos are taken in unconstrained settings, recognizing the identities of people among the…

Neural networks based on metric recognition methods have a strictly determined architecture. Number of neurons, connections, as well as weights and thresholds values are calculated analytically, based on the initial conditions of tasks:…

Face recognition is a biometric which is attracting significant research, commercial and government interest, as it provides a discreet, non-intrusive way of detecting, and recognizing individuals, without need for the subject's knowledge…

Non-rigid registration is a necessary but challenging task in medical imaging studies. Recently, unsupervised registration models have shown good performance, but they often require a large-scale training dataset and long training times.…

Current non-rigid structure from motion (NRSfM) algorithms are mainly limited with respect to: (i) the number of images, and (ii) the type of shape variability they can handle. This has hampered the practical utility of NRSfM for many…

Neural View Synthesis (NVS) has demonstrated efficacy in generating high-fidelity dense viewpoint videos using a image set with sparse views. However, existing quality assessment methods like PSNR, SSIM, and LPIPS are not tailored for the…

In this paper, we propose a learning-based framework for non-rigid shape registration without correspondence supervision. Traditional shape registration techniques typically rely on correspondences induced by extrinsic proximity, therefore…

The contribution of this paper is fourfold. The first contribution is a novel, generic method for automatic ground truth generation of camera-captured document images (books, magazines, articles, invoices, etc.). It enables us to build…

In contrast to conventional, univariate analysis, various types of multivariate analysis have been applied to functional magnetic resonance imaging (fMRI) data. In this paper, we compare two contemporary approaches for multivariate…

Foundation models, pre-trained on large image datasets and capable of capturing rich feature representations, have recently shown potential for zero-shot image registration. However, their performance has mostly been tested in the context…

We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences. The advantage of the feature-metric projection…

Kernel methods are an extremely popular set of techniques used for many important machine learning and data analysis applications. In addition to having good practical performances, these methods are supported by a well-developed theory.…

The identification of continuous-time (CT) systems from discrete-time (DT) input and output signals, i.e., the sampled data, has received considerable attention for half a century. The state-of-the-art methods are parametric methods and…

The goal of image registration is to establish spatial correspondence between two or more images, traditionally through dense displacement fields (DDFs) or parametric transformations (e.g., rigid, affine, and splines). Rethinking the…