9 accepted papers
Accurately reconstructing object edges is a key challenge in single image super-resolution (SISR), as it greatly influences our visual perception of image quality. To address this fundamental issue, we propose a novel SISR approach named the deformable attention-based edge-aware (DAE) network. The D…
Human pose estimation in computer vision is particularly challenging with images containing multiple individuals. Existing methods often integrate spatial and channel attention by simply adding them up through a cascade or parallel connection. The features extracted in this way could lead to less ac…
Corner detection is extensively applied across various computer vision tasks. Current corner detectors typically assume that the distance between every two nearby pixels is constant. However, this assumption is invalid in real-world scenarios. As a result, the pixel-based curvature measurements desi…
Existing methods for ellipse detection popularly adopt the edge-linking strategy—i.e., first combining the elliptical arcs extracted from an edge map into groups and then fitting each group of arcs to an ellipse. However, such methods generally use the Canny operator to extract edges, which tends to…
A common practice of existing ellipse detection methods is to produce an ellipse by grouping elliptic arcs. Thus, the quality (i.e., continuity) of elliptic arcs will have a significant impact on the performance of ellipse detection. In this paper, a novel contrast-guided ellipse detection method is…
Edge-drawing methods have gained increasing popularity in line segment detection due to their notable efficiency. However, existing algorithms commonly impose a pre-determined threshold on the gradient magnitude of the input image to control false positives, which could lead to the detection of line…
A novel content-based multi-scale network (CMNet) is proposed in this paper for conducting single image super-resolution (SISR). Its core lies in a content-based multi-scale image representation (CMIR), which is motivated by the fact that the contents of real-world images normally have different sca…
Line segment matching between two images of the same scene is popularly performed with the assistant of feature point correspondences. However, each existing method only relies on one specific kind of feature points to establish the correspondences, and could yield inferior performance when insuffic…
Existing methods for optical flow estimation can perform well on images with small offsets of large objects. However, they could fail when there are a number of small and fast-moving objects. In particular, current deep learning methods often impose a down-sampling of the input data for a reduction…