Edge-guided Composition Network for Image Stitching

作者：

Highlights：

• We propose a novel deep learning framework for composition in image stitching.

• We illustrate the importance of structure consistency preserving in image composition, and leverage the structure prior provided by a proposed perceptual edge branch to further enhance the composition performance.

• We build a Real Image Stitching Dataset (RISD), which is the first general-purpose benchmark for image stitching training.

摘要

•We propose a novel deep learning framework for composition in image stitching.•We illustrate the importance of structure consistency preserving in image composition, and leverage the structure prior provided by a proposed perceptual edge branch to further enhance the composition performance.•We build a Real Image Stitching Dataset (RISD), which is the first general-purpose benchmark for image stitching training.

论文关键词：Image stitching,Composition,Deep learning,Structure consistency,Edge guidance

论文评审过程：Received 31 August 2020, Revised 24 April 2021, Accepted 1 May 2021, Available online 15 May 2021, Version of Record 28 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108019