Related papers: A Light-weight Transformer-based Self-supervised M…
We address a core problem of computer vision: Detection and description of 2D feature points for image matching. For a long time, hand-crafted designs, like the seminal SIFT algorithm, were unsurpassed in accuracy and efficiency. Recently,…
This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark…
Image deblurring aims to recover the latent sharp image from its blurry counterpart and has a wide range of applications in computer vision. The Convolution Neural Networks (CNNs) have performed well in this domain for many years, and until…
Remote sensing scene classification plays a key role in Earth observation by enabling the automatic identification of land use and land cover (LULC) patterns from aerial and satellite imagery. Despite recent progress with convolutional…
We explore the application of Vision Transformer (ViT) for handwritten text recognition. The limited availability of labeled data in this domain poses challenges for achieving high performance solely relying on ViT. Previous…
Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource…
Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on…
We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and…
Image Super-Resolution (SR) aims to recover a high-resolution image from its low-resolution counterpart, which has been affected by a specific degradation process. This is achieved by enhancing detail and visual quality. Recent advancements…
Image alignment tasks require accurate pixel correspondences, which are usually recovered by matching local feature descriptors. Such descriptors are often derived using supervised learning on existing datasets with ground truth…
Computer vision and image processing applications suffer from dark and low-light images, particularly during real-time image transmission. Currently, low light and dark images are converted to bright and colored forms using autoencoders;…
High Dynamic Range (HDR) imaging aims to reproduce the wide range of brightness levels present in natural scenes, which the human visual system can perceive but conventional digital cameras often fail to capture due to their limited dynamic…
Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost. However, compressing Transformer remains as an open problem due to its internal complexity of the layer designs, i.e., Multi-Head…
Table detection within document images is a crucial task in document processing, involving the identification and localization of tables. Recent strides in deep learning have substantially improved the accuracy of this task, but it still…
Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of…
Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics. This paper proposes an unsupervised defect detection algorithm based on a…
Establishing accurate and representative matches is a crucial step in addressing the point cloud registration problem. A commonly employed approach involves detecting keypoints with salient geometric features and subsequently mapping these…
Image matching that finding robust and accurate correspondences across images is a challenging task under extreme conditions. Capturing local and global features simultaneously is an important way to mitigate such an issue but recent…
Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient high-quality labeled data…
We here propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs).…