# Fast Full-frame Video Stabilization with Iterative Optimization

arXiv: https://arxiv.org/abs/2307.12774 · HTML: https://mlsanity.com/paper/2307.12774/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 61 references that are in the map.
- First posted on arXiv 24 Jul 2023.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications](https://mlsanity.com/paper/1605.01710/) (2016)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [Generalized Video Deblurring for Dynamic Scenes](https://mlsanity.com/paper/1507.02438/) (2015)
- [Painting Outside the Box: Image Outpainting with GANs](https://mlsanity.com/paper/1808.08483/) (2018)
- [Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences](https://mlsanity.com/paper/2203.04279/) (2022)
- [Deep Iterative Frame Interpolation for Full-frame Video Stabilization](https://mlsanity.com/paper/1909.02641/) (2019)
- [Hybrid Neural Fusion for Full-frame Video Stabilization](https://mlsanity.com/paper/2102.06205/) (2021)
- [Fixed Point Strategies in Data Science](https://mlsanity.com/paper/2008.02260/) (2020)
- [DUT: Learning Video Stabilization by Simply Watching Unstable Videos](https://mlsanity.com/paper/2011.14574/) (2020)
- [Deep Online Fused Video Stabilization](https://mlsanity.com/paper/2102.01279/) (2021)
- [Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization](https://mlsanity.com/paper/2108.09041/) (2021)
- [Learning Second-Order Attentive Context for Efficient Correspondence Pruning](https://mlsanity.com/paper/2303.15761/) (2023)
- [A2B: Anchor to Barycentric Coordinate for Robust Correspondence](https://mlsanity.com/paper/2306.02760/) (2023)
- [Learning Probabilistic Coordinate Fields for Robust Correspondences](https://mlsanity.com/paper/2306.04231/) (2023)

## Built on by (most cited first, 8 of 8)

- [3D Multi-frame Fusion for Video Stabilization](https://mlsanity.com/paper/2404.12887/) (2024)
- [GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering](https://mlsanity.com/paper/2506.23957/) (2025)
- [Learning Flow-Guided Registration for RGB-Event Semantic Segmentation](https://mlsanity.com/paper/2505.01548/) (2025)
- [Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation](https://mlsanity.com/paper/2504.00401/) (2025)
- [Active Convolved Illumination with Deep Transfer Learning for Complex Beam Transmission through Atmospheric Turbulence](https://mlsanity.com/paper/2512.19540/) (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)
- [Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline](https://mlsanity.com/paper/2603.26055/) (2026)

## Abstract (arXiv)

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in video stabilization. Inspired by the analogy between wobbly frames and jigsaw puzzles, we propose an iterative optimization-based learning approach using synthetic datasets for video stabilization, which consists of two interacting submodules: motion trajectory smoothing and full-frame outpainting. First, we develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. The confidence map associated with the estimated optical flow is exploited to guide the search for shared regions through backpropagation. Second, we take a divide-and-conquer approach and propose a novel multiframe fusion strategy to render full-frame stabilized views. An important new insight brought about by our iterative optimization approach is that the target video can be interpreted as the fixed point of nonlinear mapping for video stabilization. We formulate video stabilization as a problem of minimizing the amount of jerkiness in motion trajectories, which guarantees convergence with the help of fixed-point theory. Extensive experimental results are reported to demonstrate the superiority of the proposed approach in terms of computational speed and visual quality. The code will be available on GitHub.