Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation
This addresses the challenge of obtaining training data for deep learning-based image stitching in real-world scenarios, though it is incremental in improving existing methods.
The paper tackled the problem of generating real-world panoramic images from multiple fisheye inputs without requiring ground truth images, by developing a weakly-supervised stitching network that achieved verified effectiveness on two real-world datasets.
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 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.