# Minimum Latency Deep Online Video Stabilization

arXiv: https://arxiv.org/abs/2212.02073 · HTML: https://mlsanity.com/paper/2212.02073/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 46 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Builds on (most cited first, 10 of 10)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Content-Aware Unsupervised Deep Homography Estimation](https://mlsanity.com/paper/1909.05983/) (2019)
- [Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection](https://mlsanity.com/paper/2103.15346/) (2021)
- [Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation](https://mlsanity.com/paper/2107.02524/) (2021)
- [Deep Iterative Frame Interpolation for Full-frame Video Stabilization](https://mlsanity.com/paper/1909.02641/) (2019)
- [Unsupervised Homography Estimation with Coplanarity-Aware GAN](https://mlsanity.com/paper/2205.03821/) (2022)
- [DUT: Learning Video Stabilization by Simply Watching Unstable Videos](https://mlsanity.com/paper/2011.14574/) (2020)
- [Real-Time Selfie Video Stabilization](https://mlsanity.com/paper/2009.02007/) (2020)
- [DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration](https://mlsanity.com/paper/1912.05131/) (2019)
- [StableNet: Semi-Online, Multi-Scale Deep Video Stabilization](https://mlsanity.com/paper/1907.10283/) (2019)

## Built on by (most cited first, 13 of 13)

- [Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video](https://mlsanity.com/paper/2412.06424/) (2024)
- [RecDiffusion: Rectangling for Image Stitching with Diffusion Models](https://mlsanity.com/paper/2403.19164/) (2024)
- [Supervised Homography Learning with Realistic Dataset Generation](https://mlsanity.com/paper/2307.15353/) (2023)
- [Harnessing Meta-Learning for Improving Full-Frame Video Stabilization](https://mlsanity.com/paper/2403.03662/) (2024)
- [GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering](https://mlsanity.com/paper/2506.23957/) (2025)
- [Eliminating Warping Shakes for Unsupervised Online Video Stitching](https://mlsanity.com/paper/2403.06378/) (2024)
- [StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps](https://mlsanity.com/paper/2505.05001/) (2025)
- [CodingHomo: Bootstrapping Deep Homography With Video Coding](https://mlsanity.com/paper/2504.12165/) (2025)
- [Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization](https://mlsanity.com/paper/2508.18859/) (2025)
- [Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting](https://mlsanity.com/paper/2512.05113/) (2025)
- [EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration](https://mlsanity.com/paper/2509.07662/) (2025)
- [No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors](https://mlsanity.com/paper/2602.23141/) (2026)
- [VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstruction](https://mlsanity.com/paper/2603.05851/) (2026)

## Abstract (arXiv)

We present a novel camera path optimization framework for the task of online video stabilization. Typically, a stabilization pipeline consists of three steps: motion estimating, path smoothing, and novel view rendering. Most previous methods concentrate on motion estimation, proposing various global or local motion models. In contrast, path optimization receives relatively less attention, especially in the important online setting, where no future frames are available. In this work, we adopt recent off-the-shelf high-quality deep motion models for motion estimation to recover the camera trajectory and focus on the latter two steps. Our network takes a short 2D camera path in a sliding window as input and outputs the stabilizing warp field of the last frame in the window, which warps the coming frame to its stabilized position. A hybrid loss is well-defined to constrain the spatial and temporal consistency. In addition, we build a motion dataset that contains stable and unstable motion pairs for the training. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art online methods both qualitatively and quantitatively and achieves comparable performance to offline methods. Our code and dataset are available at https://github.com/liuzhen03/NNDVS