Related papers: MatChA: Cross-Algorithm Matching with Feature Augm…
The standard approach for visual place recognition is to use global image descriptors to retrieve the most similar database images for a given query image. The results can then be further improved with re-ranking methods that re-order the…
Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this setting due to their weak semantic priors, while large…
Image matching is still challenging in such scenes with large viewpoints or illumination changes or with low textures. In this paper, we propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from…
Applications in the field of augmented reality or robotics often require joint localisation and 6D pose estimation of multiple objects. However, most algorithms need one network per object class to be trained in order to provide the best…
Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By…
Map-free relocalization technology is crucial for applications in autonomous navigation and augmented reality, but relying on pre-built maps is often impractical. It faces significant challenges due to limitations in matching methods and…
MeanShift algorithm has been widely used in tracking tasks because of its simplicity and efficiency. However, the traditional MeanShift algorithm needs to label the initial region of the target, which reduces the applicability of the…
Supervised classification and representation learning are two widely used classes of methods to analyze multivariate images. Although complementary, these methods have been scarcely considered jointly in a hierarchical modeling. In this…
We propose a new algorithm for color transfer between images that have perceptually similar semantic structures. We aim to achieve a more accurate color transfer that leverages semantically-meaningful dense correspondence between images. To…
Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead of the more common sparse paradigm, thus striving to find…
Feature matching is a crucial technique in computer vision. A unified perspective for this task is to treat it as a searching problem, aiming at an efficient search strategy to narrow the search space to point matches between images. One of…
Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied. In this paper, we investigate a new perspective of facial landmark detection and demonstrate it leads to further notable improvement.…
Deep learning (DL) algorithms have shown significant performance in various computer vision tasks. However, having limited labelled data lead to a network overfitting problem, where network performance is bad on unseen data as compared to…
Detector-based and detector-free matchers are only applicable within their respective sparsity ranges. To improve adaptability of existing matchers, this paper introduces a novel probabilistic reweighting method. Our method is applicable to…
Local feature matching aims at establishing sparse correspondences between a pair of images. Recently, detector-free methods present generally better performance but are not satisfactory in image pairs with large scale differences. In this…
Grounding-based vision and language models have been successfully applied to low-level vision tasks, aiming to precisely locate objects referred in captions. The effectiveness of grounding representation learning heavily relies on the scale…
Data augmentation refers to the process of applying a series of transformations or expansions to original data to generate new samples, thereby increasing the diversity and quantity of the data, effectively improving the performance and…
Recent Reference-Based image super-resolution (RefSR) has improved SOTA deep methods introducing attention mechanisms to enhance low-resolution images by transferring high-resolution textures from a reference high-resolution image. The main…
Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the…
Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and…