Related papers: Reference image selection for difference imaging a…
In photography, low depth of field (DOF) is an important technique to emphasize the object of interest (OOI) within an image. Thus, low DOF images are widely used in the application area of macro, portrait or sports photography. When…
Fine-Grained Image Retrieval~(FGIR) faces challenges in learning discriminative visual representations to retrieve images with similar fine-grained features. Current leading FGIR solutions typically follow two regimes: enforce pairwise…
Predictive modelling using machine learning has become very popular for spatial mapping of the environment. Models are often applied to make predictions far beyond sampling locations where new geographic locations might considerably differ…
Image similarity has been extensively studied in computer vision. In recent years, machine-learned models have shown their ability to encode more semantics than traditional multivariate metrics. However, in labelling semantic similarity,…
Generalization of deep-learning-based (DL) computer vision algorithms to various image perturbations is hard to establish and remains an active area of research. The majority of past analyses focused on the images already captured, whereas…
Feature selection is an important problem in high-dimensional data analysis and classification. Conventional feature selection approaches focus on detecting the features based on a redundancy criterion using learning and feature searching…
Image Quality Assessment (IQA) with reference images have achieved great success by imitating the human vision system, in which the image quality is effectively assessed by comparing the query image with its pristine reference image.…
It is a common paradigm in object detection frameworks to treat all samples equally and target at maximizing the performance on average. In this work, we revisit this paradigm through a careful study on how different samples contribute to…
Image quality assessment (IQA) is traditionally classified into full-reference (FR) IQA and no-reference (NR) IQA according to whether the original image is required. Although NR-IQA is widely used in practical applications, room for…
Enhancing low-light images while maintaining natural colors is a challenging problem due to camera processing variations and limited access to photos with ground-truth lighting conditions. The latter is a crucial factor for supervised…
We propose an image representation and matching approach that substantially improves visual-based location estimation for images. The main novelty of the approach, called distinctive visual element matching (DVEM), is its use of…
We examine the challenge of estimating the location of a single ground-level image in the absence of GPS or other location metadata. Currently, geolocation systems are evaluated by measuring the Great Circle Distance between the predicted…
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from…
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we…
Visual relation detection methods rely on object information extracted from RGB images such as 2D bounding boxes, feature maps, and predicted class probabilities. We argue that depth maps can additionally provide valuable information on…
Nowadays, photogrammetrically derived point clouds are widely used in many civilian applications due to their low cost and flexibility in acquisition. Typically, photogrammetric point clouds are assessed through reference data such as LiDAR…
Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particularly important in remote sensing, where data acquisition is costly and annotation often…
Image retrieval methods rely on metric learning to train backbone feature extraction models that can extract discriminant queries and reference (gallery) feature representations for similarity matching. Although state-of-the-art accuracy…
In the feature classification domain, the choice of data affects widely the results. For the Hyperspectral image, the bands dont all contain the information; some bands are irrelevant like those affected by various atmospheric effects, see…
Change detection, which typically relies on the comparison of bi-temporal images, is significantly hindered when only a single image is available. Comparing a single image with an existing map, such as OpenStreetMap, which is continuously…