# Robust image stitching with multiple registrations

arXiv: https://arxiv.org/abs/2011.11784 · HTML: https://mlsanity.com/paper/2011.11784/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations](https://mlsanity.com/paper/2103.15982/) (2021)
- [Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation](https://mlsanity.com/paper/2209.05968/) (2022)
- [Natural Image Stitching Using Depth Maps](https://mlsanity.com/paper/2202.06276/) (2022)
- [Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping](https://mlsanity.com/paper/2406.19922/) (2024)
- [Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptors](https://mlsanity.com/paper/2209.11795/) (2022)
- [Leveraging Local Patch Alignment to Seam-cutting for Large Parallax Image Stitching](https://mlsanity.com/paper/2311.18564/) (2023)

## Abstract (arXiv)

Panorama creation is one of the most widely deployed techniques in computer vision. In addition to industry applications such as Google Street View, it is also used by millions of consumers in smartphones and other cameras. Traditionally, the problem is decomposed into three phases: registration, which picks a single transformation of each source image to align it to the other inputs, seam finding, which selects a source image for each pixel in the final result, and blending, which fixes minor visual artifacts. Here, we observe that the use of a single registration often leads to errors, especially in scenes with significant depth variation or object motion. We propose instead the use of multiple registrations, permitting regions of the image at different depths to be captured with greater accuracy. MRF inference techniques naturally extend to seam finding over multiple registrations, and we show here that their energy functions can be readily modified with new terms that discourage duplication and tearing, common problems that are exacerbated by the use of multiple registrations. Our techniques are closely related to layer-based stereo, and move image stitching closer to explicit scene modeling. Experimental evidence demonstrates that our techniques often generate significantly better panoramas when there is substantial motion or parallax.