# Image Stitching Based on Planar Region Consensus

arXiv: https://arxiv.org/abs/2007.02722 · HTML: https://mlsanity.com/paper/2007.02722/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 7 of 7)

- [VDD: Varied Drone Dataset for Semantic Segmentation](https://mlsanity.com/paper/2305.13608/) (2023)
- [Parallax-Tolerant Unsupervised Deep Image Stitching](https://mlsanity.com/paper/2302.08207/) (2023)
- [Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping](https://mlsanity.com/paper/2406.19922/) (2024)
- [Parallax-Tolerant Image Stitching with Epipolar Displacement Field](https://mlsanity.com/paper/2311.16637/) (2023)
- [Robust Image Stitching with Optimal Plane](https://mlsanity.com/paper/2508.05903/) (2025)
- [LiftProj: Space Lifting and Projection-Based Panorama Stitching](https://mlsanity.com/paper/2512.24276/) (2025)
- [UniStitch: Unifying Semantic and Geometric Features for Image Stitching](https://mlsanity.com/paper/2603.10568/) (2026)

## Abstract (arXiv)

Image stitching for two images without a global transformation between them is notoriously difficult. In this paper, noticing the importance of planar structure under perspective geometry, we propose a new image stitching method which stitches images by allowing for the alignment of a set of matched dominant planar regions. Clearly different from previous methods resorting to plane segmentation, the key to our approach is to utilize rich semantic information directly from RGB images to extract planar image regions with a deep Convolutional Neural Network (CNN). We specifically design a new module to make fully use of existing semantic segmentation networks to accommodate planar segmentation. To train the network, a dataset for planar region segmentation is contributed. With the planar region knowledge, a set of local transformations can be obtained by constraining matched regions, enabling more precise alignment in the overlapping area. We also use planar knowledge to estimate a transformation field over the whole image. The final mosaic is obtained by a mesh-based optimization framework which maintains high alignment accuracy and relaxes similarity transformation at the same time. Extensive experiments with quantitative comparisons show that our method can deal with different situations and outperforms the state-of-the-arts on challenging scenes.