# Quasi-homography warps in image stitching

arXiv: https://arxiv.org/abs/1701.08006 · HTML: https://mlsanity.com/paper/1701.08006/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2017.

## Built on by (most cited first, 9 of 9)

- [Deep Rectangling for Image Stitching: A Learning Baseline](https://mlsanity.com/paper/2203.03831/) (2022)
- [Real-time Nonrigid Mosaicking of Laparoscopy Images](https://mlsanity.com/paper/2103.07414/) (2021)
- [TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models](https://mlsanity.com/paper/2309.11258/) (2023)
- [Pixel-wise Deep Image Stitching](https://mlsanity.com/paper/2112.06171/) (2021)
- [Natural Image Stitching Using Depth Maps](https://mlsanity.com/paper/2202.06276/) (2022)
- [Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting](https://mlsanity.com/paper/2411.10309/) (2024)
- [Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping](https://mlsanity.com/paper/2406.19922/) (2024)
- [NeRF-Enhanced Outpainting for Faithful Field-of-View Extrapolation](https://mlsanity.com/paper/2309.13240/) (2023)
- [LiftProj: Space Lifting and Projection-Based Panorama Stitching](https://mlsanity.com/paper/2512.24276/) (2025)

## Abstract (arXiv)

The naturalness of warps is gaining extensive attentions in image stitching. Recent warps such as SPHP and AANAP, use global similarity warps to mitigate projective distortion (which enlarges regions), however, they necessarily bring in perspective distortion (which generates inconsistencies). In this paper, we propose a novel quasi-homography warp, which effectively balances the perspective distortion against the projective distortion in the non-overlapping region to create a more natural-looking panorama. Our approach formulates the warp as the solution of a bivariate system, where perspective distortion and projective distortion are characterized as slope preservation and scale linearization respectively. Because our proposed warp only relies on a global homography, thus it is totally parameter-free. A comprehensive experiment shows that a quasi-homography warp outperforms some state-of-the-art warps in urban scenes, including homography, AutoStitch and SPHP. A user study demonstrates that it wins most users' favor, comparing to homography and SPHP.