# EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration

arXiv: https://arxiv.org/abs/2509.07662 · HTML: https://mlsanity.com/paper/2509.07662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [Deep Image Homography Estimation](https://mlsanity.com/paper/1606.03798/) (2016)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [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)
- [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](https://mlsanity.com/paper/2106.12859/) (2021)
- [Iterative Deep Homography Estimation](https://mlsanity.com/paper/2203.15982/) (2022)
- [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)
- [Single-Perspective Warps in Natural Image Stitching](https://mlsanity.com/paper/1802.04645/) (2018)
- [Unsupervised Homography Estimation with Coplanarity-Aware GAN](https://mlsanity.com/paper/2205.03821/) (2022)
- [Minimum Latency Deep Online Video Stabilization](https://mlsanity.com/paper/2212.02073/) (2022)
- [Supervised Homography Learning with Realistic Dataset Generation](https://mlsanity.com/paper/2307.15353/) (2023)
- [Eliminating Warping Shakes for Unsupervised Online Video Stitching](https://mlsanity.com/paper/2403.06378/) (2024)

## Abstract (arXiv)

Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due to their inherent limitations. To address this, we propose an Exponential-Decay Free-Form Deformation Network (EDFFDNet), which employs free-form deformation with an exponential-decay basis function. This design achieves higher efficiency and performs well in scenes with depth disparities, benefiting from its inherent locality. We also introduce an Adaptive Sparse Motion Aggregator (ASMA), which replaces the MLP motion aggregator used in previous methods. By transforming dense interactions into sparse ones, ASMA reduces parameters and improves accuracy. Additionally, we propose a progressive correlation refinement strategy that leverages global-local correlation patterns for coarse-to-fine motion estimation, further enhancing efficiency and accuracy. Experiments demonstrate that EDFFDNet reduces parameters, memory, and total runtime by 70.5%, 32.6%, and 33.7%, respectively, while achieving a 0.5 dB PSNR gain over the state-of-the-art method. With an additional local refinement stage,EDFFDNet-2 further improves PSNR by 1.06 dB while maintaining lower computational costs. Our method also demonstrates strong generalization ability across datasets, outperforming previous deep learning methods.