# Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks

arXiv: https://arxiv.org/abs/2512.03014 · HTML: https://mlsanity.com/paper/2512.03014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 63 of its 86 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 30 of 63)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)
- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [Learning Video Object Segmentation from Static Images](https://mlsanity.com/paper/1612.02646/) (2016)
- [MNIST-C: A Robustness Benchmark for Computer Vision](https://mlsanity.com/paper/1906.02337/) (2019)
- [Need for Speed: A Benchmark for Higher Frame Rate Object Tracking](https://mlsanity.com/paper/1703.05884/) (2017)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Deep Flow-Guided Video Inpainting](https://mlsanity.com/paper/1905.02884/) (2019)
- [Coherent Online Video Style Transfer](https://mlsanity.com/paper/1703.09211/) (2017)
- [Fast Patch-based Style Transfer of Arbitrary Style](https://mlsanity.com/paper/1612.04337/) (2016)
- [A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking](https://mlsanity.com/paper/2302.14301/) (2023)
- [Arbitrary Video Style Transfer via Multi-Channel Correlation](https://mlsanity.com/paper/2009.08003/) (2020)

## Abstract (arXiv)

When applied sequentially to video, frame-based networks often exhibit temporal inconsistency - for example, outputs that flicker between frames. This problem is amplified when the network inputs contain time-varying corruptions. In this work, we introduce a general approach for adapting frame-based models for stable and robust inference on video. We describe a class of stability adapters that can be inserted into virtually any architecture and a resource-efficient training process that can be performed with a frozen base network. We introduce a unified conceptual framework for describing temporal stability and corruption robustness, centered on a proposed accuracy-stability-robustness loss. By analyzing the theoretical properties of this loss, we identify the conditions where it produces well-behaved stabilizer training. Our experiments validate our approach on several vision tasks including denoising (NAFNet), image enhancement (HDRNet), monocular depth (Depth Anything v2), and semantic segmentation (DeepLabv3+). Our method improves temporal stability and robustness against a range of image corruptions (including compression artifacts, noise, and adverse weather), while preserving or improving the quality of predictions.