Related papers: RIFT: Multi-modal Image Matching Based on Radiatio…

This paper considers matching images of low-light scenes, aiming to widen the frontier of SfM and visual SLAM applications. Recent image sensors can record the brightness of scenes with more than eight-bit precision, available in their…

Rain streaks bring complicated pixel intensity changes and additional gradients, greatly obstructing the extraction of image features from background. This causes serious performance degradation in feature-based applications. Thus, it is…

This paper presents a novel appearance and shape feature, RISAS, which is robust to viewpoint, illumination, scale and rotation variations. RISAS consists of a keypoint detector and a feature descriptor both of which utilise texture and…

A vital issue of file carving in digital forensics is type classification of file fragments when the filesystem metadata is missing. Over the past decades, there have been several efforts for developing methods to classify file fragments.…

General detectors follow the pipeline that feature maps extracted from ConvNets are shared between classification and regression tasks. However, there exists obvious conflicting requirements in multi-orientation object detection that…

In recent years, due to the wide application of multi-sensor vision systems, multimodal image acquisition technology has continued to develop, and the registration problem based on multimodal images has gradually emerged. Most of the…

During the diagnostic process, doctors incorporate multimodal information including imaging and the medical history - and similarly medical AI development has increasingly become multimodal. In this paper we tackle a more subtle challenge:…

Leveraging the vision foundation models has emerged as a mainstream paradigm that improves the performance of image feature matching. However, previous works have ignored the misalignment when introducing the foundation models into feature…

In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on…

Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, reveal scalability limitations with increasing modalities as…

In this work, a simple and efficient dual iterative refinement (DIR) method is proposed for dense correspondence between two nearly isometric shapes. The key idea is to use dual information, such as spatial and spectral, or local and global…

The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so-called query image. To bridge the semantic…

This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer.…

Radio-frequency interference (RFI) is a major systematic limitation in radio astronomy, particularly for science cases requiring high sensitivity, such as 21 cm cosmology. Traditionally, RFI is dealt with by identifying its signature in the…

Local Feature Matching, an essential component of several computer vision tasks (e.g., structure from motion and visual localization), has been effectively settled by Transformer-based methods. However, these methods only integrate…

Co-registration of multimodal remote sensing images is still an ongoing challenge because of nonlinear radiometric differences (NRD) and significant geometric distortions (e.g., scale and rotation changes) between these images. In this…

In the past few years, the performance of road defect detection has been remarkably improved thanks to advancements on various studies on computer vision and deep learning. Although a large-scale and well-annotated datasets enhance the…

Vision Transformers (ViTs) have shown exceptional performance in vehicle re-identification (ReID) tasks. However, non-square aspect ratios of image or video inputs can negatively impact re-identification accuracy. To address this challenge,…

Deformable image registration (DIR) is a crucial and challenging technique for aligning anatomical structures in medical images and is widely applied in diverse clinical applications. However, existing approaches often struggle to capture…

Geospatial object detection of remote sensing imagery has been attracting an increasing interest in recent years, due to the rapid development in spaceborne imaging. Most of previously proposed object detectors are very sensitive to object…