# Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images

arXiv: https://arxiv.org/abs/2106.12859 · HTML: https://mlsanity.com/paper/2106.12859/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 53 references that are in the map.
- First posted on arXiv 24 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Deep Image Homography Estimation](https://mlsanity.com/paper/1606.03798/) (2016)
- [Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model](https://mlsanity.com/paper/1709.03966/) (2017)
- [Content-Aware Unsupervised Deep Homography Estimation](https://mlsanity.com/paper/1909.05983/) (2019)
- [Deep Homography Estimation for Dynamic Scenes](https://mlsanity.com/paper/2004.02132/) (2020)
- [Video Stitching for Linear Camera Arrays](https://mlsanity.com/paper/1907.13622/) (2019)
- [Learning Edge-Preserved Image Stitching from Large-Baseline Deep Homography](https://mlsanity.com/paper/2012.06194/) (2020)

## Built on by (most cited first, 30 of 49)

- [Parallax-Tolerant Unsupervised Deep Image Stitching](https://mlsanity.com/paper/2302.08207/) (2023)
- [Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation](https://mlsanity.com/paper/2107.02524/) (2021)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [Deep Rectangling for Image Stitching: A Learning Baseline](https://mlsanity.com/paper/2203.03831/) (2022)
- [RecDiffusion: Rectangling for Image Stitching with Diffusion Models](https://mlsanity.com/paper/2403.19164/) (2024)
- [Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation](https://mlsanity.com/paper/2209.05968/) (2022)
- [Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint](https://mlsanity.com/paper/2212.02763/) (2022)
- [Robust Image Semantic Coding with Learnable CSI Fusion Masking over MIMO Fading Channels](https://mlsanity.com/paper/2406.07389/) (2024)
- [Object-level Geometric Structure Preserving for Natural Image Stitching](https://mlsanity.com/paper/2402.12677/) (2024)
- [MOWA: Multiple-in-One Image Warping Model](https://mlsanity.com/paper/2404.10716/) (2024)
- [AbHE: All Attention-based Homography Estimation](https://mlsanity.com/paper/2212.03029/) (2022)
- [Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks](https://mlsanity.com/paper/2402.15959/) (2024)
- [Communication-Efficient Framework for Distributed Image Semantic Wireless Transmission](https://mlsanity.com/paper/2308.03713/) (2023)
- [Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond](https://mlsanity.com/paper/2401.13432/) (2024)
- [PRISM: PRogressive dependency maxImization for Scale-invariant image Matching](https://mlsanity.com/paper/2408.03598/) (2024)
- [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)
- [Multi-Spectral Image Stitching via Spatial Graph Reasoning](https://mlsanity.com/paper/2307.16741/) (2023)
- [Learning Residual Elastic Warps for Image Stitching under Dirichlet Boundary Condition](https://mlsanity.com/paper/2309.01406/) (2023)
- [Implicit Neural Image Stitching](https://mlsanity.com/paper/2309.01409/) (2023)
- [Eliminating Warping Shakes for Unsupervised Online Video Stitching](https://mlsanity.com/paper/2403.06378/) (2024)
- [Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model](https://mlsanity.com/paper/2404.14951/) (2024)
- [SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization](https://mlsanity.com/paper/2409.17993/) (2024)
- [Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting](https://mlsanity.com/paper/2411.10309/) (2024)
- [Multi-user Wireless Image Semantic Transmission over MIMO Multiple Access Channels](https://mlsanity.com/paper/2504.07969/) (2025)
- [Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations](https://mlsanity.com/paper/2402.18008/) (2024)
- [Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping](https://mlsanity.com/paper/2406.19922/) (2024)
- [StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps](https://mlsanity.com/paper/2505.05001/) (2025)
- [Deep Seam Prediction for Image Stitching Based on Selection Consistency Loss](https://mlsanity.com/paper/2302.05027/) (2023)
- [Shadow Removal by High-Quality Shadow Synthesis](https://mlsanity.com/paper/2212.04108/) (2022)

## Abstract (arXiv)

Traditional feature-based image stitching technologies rely heavily on feature detection quality, often failing to stitch images with few features or low resolution. The learning-based image stitching solutions are rarely studied due to the lack of labeled data, making the supervised methods unreliable. To address the above limitations, we propose an unsupervised deep image stitching framework consisting of two stages: unsupervised coarse image alignment and unsupervised image reconstruction. In the first stage, we design an ablation-based loss to constrain an unsupervised homography network, which is more suitable for large-baseline scenes. Moreover, a transformer layer is introduced to warp the input images in the stitching-domain space. In the second stage, motivated by the insight that the misalignments in pixel-level can be eliminated to a certain extent in feature-level, we design an unsupervised image reconstruction network to eliminate the artifacts from features to pixels. Specifically, the reconstruction network can be implemented by a low-resolution deformation branch and a high-resolution refined branch, learning the deformation rules of image stitching and enhancing the resolution simultaneously. To establish an evaluation benchmark and train the learning framework, a comprehensive real-world image dataset for unsupervised deep image stitching is presented and released. Extensive experiments well demonstrate the superiority of our method over other state-of-the-art solutions. Even compared with the supervised solutions, our image stitching quality is still preferred by users.