# Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization

arXiv: https://arxiv.org/abs/2508.18859 · HTML: https://mlsanity.com/paper/2508.18859/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 84 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 30 of 45)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://mlsanity.com/paper/2404.12390/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Meta Networks](https://mlsanity.com/paper/1703.00837/) (2017)
- [Generative Judge for Evaluating Alignment](https://mlsanity.com/paper/2310.05470/) (2023)
- [Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators](https://mlsanity.com/paper/2403.16950/) (2024)
- [The Contextual Loss for Image Transformation with Non-Aligned Data](https://mlsanity.com/paper/1803.02077/) (2018)
- [VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding](https://mlsanity.com/paper/2412.03735/) (2024)
- [Tracking by Instance Detection: A Meta-Learning Approach](https://mlsanity.com/paper/2004.00830/) (2020)
- [Fast Adaptation to Super-Resolution Networks via Meta-Learning](https://mlsanity.com/paper/2001.02905/) (2020)
- [Self-Supervised Video Representation Learning with Meta-Contrastive Network](https://mlsanity.com/paper/2108.08426/) (2021)
- [Deep Iterative Frame Interpolation for Full-frame Video Stabilization](https://mlsanity.com/paper/1909.02641/) (2019)
- [VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation](https://mlsanity.com/paper/2502.12782/) (2025)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [Hybrid Neural Fusion for Full-frame Video Stabilization](https://mlsanity.com/paper/2102.06205/) (2021)
- [Scene-Adaptive Video Frame Interpolation via Meta-Learning](https://mlsanity.com/paper/2004.00779/) (2020)
- [Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning](https://mlsanity.com/paper/2111.15056/) (2021)
- [DUT: Learning Video Stabilization by Simply Watching Unstable Videos](https://mlsanity.com/paper/2011.14574/) (2020)
- [One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video](https://mlsanity.com/paper/2103.12988/) (2021)
- [MetaPix: Few-Shot Video Retargeting](https://mlsanity.com/paper/1910.04742/) (2019)

## Built on by (most cited first, 2 of 2)

- [Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models](https://mlsanity.com/paper/2510.13315/) (2025)
- [Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding](https://mlsanity.com/paper/2604.13313/) (2026)

## Abstract (arXiv)

Video stabilization remains a fundamental problem in computer vision, particularly pixel-level synthesis solutions for video stabilization, which synthesize full-frame outputs, add to the complexity of this task. These methods aim to enhance stability while synthesizing full-frame videos, but the inherent diversity in motion profiles and visual content present in each video sequence makes robust generalization with fixed parameters difficult. To address this, we present a novel method that improves pixel-level synthesis video stabilization methods by rapidly adapting models to each input video at test time. The proposed approach takes advantage of low-level visual cues available during inference to improve both the stability and visual quality of the output. Notably, the proposed rapid adaptation achieves significant performance gains even with a single adaptation pass. We further propose a jerk localization module and a targeted adaptation strategy, which focuses the adaptation on high-jerk segments for maximizing stability with fewer adaptation steps. The proposed methodology enables modern stabilizers to overcome the longstanding SOTA approaches while maintaining the full frame nature of the modern methods, while offering users with control mechanisms akin to classical approaches. Extensive experiments on diverse real-world datasets demonstrate the versatility of the proposed method. Our approach consistently improves the performance of various full-frame synthesis models in both qualitative and quantitative terms, including results on downstream applications.