Shape-Preserving Half-Projective Warps for Image Stitching

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 3254 - 3261
• Main Authors: Che-Han Chang, Sato, Yoichi, Yung-Yu Chuang
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Accuracy; Alignment; Cameras; Computer vision; Educational institutions; Equations; Jacobian matrices; Pattern recognition; Shape; Similarity; Stitching; Transformations; Transforms; Warp
• ISSN: 1063-6919; 1063-6919; 2575-7075
• DOI: 10.1109/CVPR.2014.422

This paper proposes a novel parametric warp which is a spatial combination of a projective transformation and a similarity transformation. Given the projective transformation relating two input images, based on an analysis of the projective transformation, our method smoothly extrapolates the projective transformation of the overlapping regions into the non-overlapping regions and the resultant warp gradually changes from projective to similarity across the image. The proposed warp has the strengths of both projective and similarity warps. It provides good alignment accuracy as projective warps while preserving the perspective of individual image as similarity warps. It can also be combined with more advanced local-warp-based alignment methods such as the as-projective-as-possible warp for better alignment accuracy. With the proposed warp, the field of view can be extended by stitching images with less projective distortion (stretched shapes and enlarged sizes).