图像拼接任务对于目前主流视觉任务来说比较偏,目前基于深度学习的框架还不成熟,而且拼接任务里面很多小点都可以单独拿出来研究,比如聚焦或迁移到单应矩阵,图像对齐,图像融合,视频防抖,图像矩形化等。找到好的研究场景,既能发文又能有实用价值。现简单整理近几年的相关文章,如有遗漏还望读者指出。
-
Natural Image Stitching Using Depth Maps
-
Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images
-
Pixel-wise Deep Image Stitching
-
Learning Edge-Preserved Image Stitching from Large-Baseline Deep Homography
-
A view-free image stitching network based on global homography
-
A Novel Projective-Consistent Plane Based Image Stitching Method
-
Graph-based Hypothesis Generation for Parallax-tolerant Image Stitching
-
Single-Perspective Warps in Natural Image Stitching
-
Parallax-Tolerant Image Stitching Based on Robust Elastic Warping