VIP Lab’s paper accepted to CVPR 2020
UNIST ECE student, Kyu-Yul Lee and Prof. Jae-Young Sim’s paper has been accepted to CVPR 2020.
Authors: Kyu-Yul Lee and Jae-Young Sim (corresponding author)
Title: Warping Residual Based Image Stitching for Large Parallax
Conference: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Image stitching techniques align two images captured at different viewing positions onto a single wider image. When the captured 3D scene is not planar and the camera baseline is large, two images exhibit parallax where the relative positions of scene structures are quite different from each view. The existing image stitching methods often fail to work on the images with large parallax. In this paper,we propose a reliable image stitching algorithm robust to large parallax based on the novel concept of warping residuals. We ﬁrst estimate multiple homographies and find their inlier feature matches, respectively, between two images. Then we evaluate warping residual for each feature match with respect to the multiple homographies. To alleviate the parallax artifacts, we partition input images into superpixels and warp each superpixel adaptively according to an optimal homography which is computed by minimizing the error of feature matches weighted by the warping residuals.
CVPR is an annual conference on computer vision and pattern recognition published by IEEE. CVPR is regarded as the most prestige conference in computer vision and also ranked 2nd among engineering & computer science in Google Scholar. The acceptance rate of CVPR 2020 is 22%.