BROWSE
Detail
Conference Paper
Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation
Cited 21 time in 
Share 
Share
- Authors
- Dae-Young Song, Geonsoo Lee, HeeKyung Lee, Gi-Mun Um, Donghyeon Cho
- Issue Date
- 2022-10
- Citation
- European Conference on Computer Vision (ECCV) 2022 (LNCS 13676), pp.54-71
- Publisher
- Springer
- Language
- English
- Type
- Conference Paper
- Abstract
- Recently, there has been growing attention on an end-to-end deep learning-based stitching model. However, the most challenging point in deep learning-based stitching is to obtain pairs of input images with a narrow field of view and ground truth images with a wide field of view captured from real-world scenes. To overcome this difficulty, we develop a weakly-supervised learning mechanism to train the stitching model without requiring genuine ground truth images. In addition, we propose a stitching model that takes multiple real-world fisheye images as inputs and creates a 360 ?닔 output image in an equirectangular projection format. In particular, our model consists of color consistency corrections, warping, and blending, and is trained by perceptual and SSIM losses. The effectiveness of the proposed algorithm is verified on two real-world stitching datasets.
- KSP Keywords
- End to End(E2E), Field of View(FoV), Ground Truth, Learning-based, Panoramic image, Real-world, Weakly supervised learning, Wide field, deep learning(DL), fisheye images, image generation