360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares

TL;DR

This paper presents a novel rigid moving least squares-based method for stitching dual-fisheye lens images into high-quality 360-degree videos, addressing overlap limitations and jitter issues for improved user-generated content.

Contribution

Introduces a new image alignment technique using interpolation grids and a boundary coherence algorithm to produce seamless, jitter-free 360-degree videos from dual-fisheye cameras.

Findings

Higher quality stitched images compared to prior methods

Jitter-free 360-degree videos achieved

Effective handling of limited overlap in dual-fisheye images

Abstract

Dual-fisheye lens cameras are becoming popular for 360-degree video capture, especially for User-generated content (UGC), since they are affordable and portable. Images generated by the dual-fisheye cameras have limited overlap and hence require non-conventional stitching techniques to produce high-quality 360x180-degree panoramas. This paper introduces a novel method to align these images using interpolation grids based on rigid moving least squares. Furthermore, jitter is the critical issue arising when one applies the image-based stitching algorithms to video. It stems from the unconstrained movement of stitching boundary from one frame to another. Therefore, we also propose a new algorithm to maintain the temporal coherence of stitching boundary to provide jitter-free 360-degree videos. Results show that the method proposed in this paper can produce higher quality stitched images and videos than prior work.