# Characterizing and Improving Stability in Neural Style Transfer

arXiv: https://arxiv.org/abs/1705.02092 · HTML: https://mlsanity.com/paper/1705.02092/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2017.

## Built on by (most cited first, 30 of 31)

- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [Stylizing 3D Scene via Implicit Representation and HyperNetwork](https://mlsanity.com/paper/2105.13016/) (2021)
- [Learning to Stylize Novel Views](https://mlsanity.com/paper/2105.13509/) (2021)
- [StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions](https://mlsanity.com/paper/2112.01530/) (2021)
- [CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer](https://mlsanity.com/paper/2207.04808/) (2022)
- [CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer](https://mlsanity.com/paper/2303.17867/) (2023)
- [VToonify: Controllable High-Resolution Portrait Video Style Transfer](https://mlsanity.com/paper/2209.11224/) (2022)
- [Gaussian Splatting in Style](https://mlsanity.com/paper/2403.08498/) (2024)
- [Visual Affordance Prediction for Guiding Robot Exploration](https://mlsanity.com/paper/2305.17783/) (2023)
- [STRIVE: Scene Text Replacement In Videos](https://mlsanity.com/paper/2109.02762/) (2021)
- [The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting](https://mlsanity.com/paper/2105.05332/) (2021)
- [Location-Free Camouflage Generation Network](https://mlsanity.com/paper/2203.09845/) (2022)
- [Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generation](https://mlsanity.com/paper/2407.14774/) (2024)
- [Automatic Non-Linear Video Editing Transfer](https://mlsanity.com/paper/2105.06988/) (2021)
- [Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow](https://mlsanity.com/paper/2201.05723/) (2022)
- [Frame Difference-Based Temporal Loss for Video Stylization](https://mlsanity.com/paper/2102.05822/) (2021)
- [MuVieCAST: Multi-View Consistent Artistic Style Transfer](https://mlsanity.com/paper/2312.05046/) (2023)
- [Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient](https://mlsanity.com/paper/2410.20657/) (2024)
- [Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting](https://mlsanity.com/paper/2509.26455/) (2025)
- [CAMS: Color-Aware Multi-Style Transfer](https://mlsanity.com/paper/2106.13920/) (2021)
- [Two Decades of Colorization and Decolorization for Images and Videos](https://mlsanity.com/paper/2204.13322/) (2022)
- [Efficient Video Segmentation Models with Per-frame Inference](https://mlsanity.com/paper/2202.12427/) (2022)
- [Interactive Control over Temporal Consistency while Stylizing Video Streams](https://mlsanity.com/paper/2301.00750/) (2023)
- [G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Styles](https://mlsanity.com/paper/2408.13508/) (2024)
- [Iris Style Transfer: Enhancing Iris Recognition with Style Features and Privacy Preservation through Neural Style Transfer](https://mlsanity.com/paper/2503.04707/) (2025)
- [Trade-offs in Privacy-Preserving Eye Tracking through Iris Obfuscation: A Benchmarking Study](https://mlsanity.com/paper/2504.10267/) (2025)
- [LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer](https://mlsanity.com/paper/2512.18930/) (2025)
- [WAIT: Feature Warping for Animation to Illustration video Translation using GANs](https://mlsanity.com/paper/2310.04901/) (2023)
- [Adapting MIMO video restoration networks to low latency constraints](https://mlsanity.com/paper/2408.12439/) (2024)
- [Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation](https://mlsanity.com/paper/2509.22307/) (2025)

## Abstract (arXiv)

Recent progress in style transfer on images has focused on improving the quality of stylized images and speed of methods. However, real-time methods are highly unstable resulting in visible flickering when applied to videos. In this work we characterize the instability of these methods by examining the solution set of the style transfer objective. We show that the trace of the Gram matrix representing style is inversely related to the stability of the method. Then, we present a recurrent convolutional network for real-time video style transfer which incorporates a temporal consistency loss and overcomes the instability of prior methods. Our networks can be applied at any resolution, do not re- quire optical flow at test time, and produce high quality, temporally consistent stylized videos in real-time.