# Blind Video Deflickering by Neural Filtering with a Flawed Atlas

arXiv: https://arxiv.org/abs/2303.08120 · HTML: https://mlsanity.com/paper/2303.08120/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 66 references that are in the map.
- First posted on arXiv 14 Mar 2023.

## Builds on (most cited first, 30 of 36)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Text2LIVE: Text-Driven Layered Image and Video Editing](https://mlsanity.com/paper/2204.02491/) (2022)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Layered Neural Atlases for Consistent Video Editing](https://mlsanity.com/paper/2109.11418/) (2021)
- [Blind Video Temporal Consistency via Deep Video Prior](https://mlsanity.com/paper/2010.11838/) (2020)
- [Deep Exemplar-based Video Colorization](https://mlsanity.com/paper/1906.09909/) (2019)
- [Polarized Reflection Removal with Perfect Alignment in the Wild](https://mlsanity.com/paper/2003.12789/) (2020)
- [High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization](https://mlsanity.com/paper/2211.15662/) (2022)
- [Deformable Sprites for Unsupervised Video Decomposition](https://mlsanity.com/paper/2204.07151/) (2022)
- [Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image](https://mlsanity.com/paper/2203.09457/) (2022)
- [ViDeNN: Deep Blind Video Denoising](https://mlsanity.com/paper/1904.10898/) (2019)
- [Fully Automatic Video Colorization with Self-Regularization and Diversity](https://mlsanity.com/paper/1908.01311/) (2019)
- [Bringing Old Films Back to Life](https://mlsanity.com/paper/2203.17276/) (2022)
- [Learning Implicit Feature Alignment Function for Semantic Segmentation](https://mlsanity.com/paper/2206.08655/) (2022)
- [Temporally Consistent Semantic Video Editing](https://mlsanity.com/paper/2206.10590/) (2022)

## Built on by (most cited first, 27 of 27)

- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models](https://mlsanity.com/paper/2404.16306/) (2024)
- [Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer](https://mlsanity.com/paper/2305.05464/) (2023)
- [Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization](https://mlsanity.com/paper/2504.03011/) (2025)
- [DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis](https://mlsanity.com/paper/2308.03463/) (2023)
- [Automatic Controllable Colorization via Imagination](https://mlsanity.com/paper/2404.05661/) (2024)
- [NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation](https://mlsanity.com/paper/2307.08695/) (2023)
- [Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models](https://mlsanity.com/paper/2401.16224/) (2024)
- [FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration](https://mlsanity.com/paper/2311.15445/) (2023)
- [Sketch Video Synthesis](https://mlsanity.com/paper/2311.15306/) (2023)
- [BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes](https://mlsanity.com/paper/2510.09996/) (2025)
- [SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation](https://mlsanity.com/paper/2303.11591/) (2023)
- [FastBlend: a Powerful Model-Free Toolkit Making Video Stylization Easier](https://mlsanity.com/paper/2311.09265/) (2023)
- [Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion](https://mlsanity.com/paper/2405.20032/) (2024)
- [Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos](https://mlsanity.com/paper/2410.11828/) (2024)
- [Instruct-NeuralTalker: Editing Audio-Driven Talking Radiance Fields with Instructions](https://mlsanity.com/paper/2306.10813/) (2023)
- [L-C4: Language-Based Video Colorization for Creative and Consistent Color](https://mlsanity.com/paper/2410.04972/) (2024)
- [Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency](https://mlsanity.com/paper/2411.16468/) (2024)
- [Loopy: Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding](https://mlsanity.com/paper/2608.23090/) (2026)
- [BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering](https://mlsanity.com/paper/2403.06243/) (2024)
- [MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction](https://mlsanity.com/paper/2505.13839/) (2025)
- [Autobiasing Event Cameras for Flickering Mitigation](https://mlsanity.com/paper/2511.02180/) (2025)
- [HarmoVid: Relightful Video Portrait Harmonization](https://mlsanity.com/paper/2605.28811/) (2026)
- [Generative Relightable Avatars](https://mlsanity.com/paper/2606.22718/) (2026)
- [DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Data](https://mlsanity.com/paper/2606.27576/) (2026)
- [Revisiting the Current Frame: Physical-Trace-Guided Network Output Correction for Video Restoration](https://mlsanity.com/paper/2608.09342/) (2026)
- [Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy](https://mlsanity.com/paper/2609.34381/) (2026)

## Abstract (arXiv)

Many videos contain flickering artifacts. Common causes of flicker include video processing algorithms, video generation algorithms, and capturing videos under specific situations. Prior work usually requires specific guidance such as the flickering frequency, manual annotations, or extra consistent videos to remove the flicker. In this work, we propose a general flicker removal framework that only receives a single flickering video as input without additional guidance. Since it is blind to a specific flickering type or guidance, we name this "blind deflickering." The core of our approach is utilizing the neural atlas in cooperation with a neural filtering strategy. The neural atlas is a unified representation for all frames in a video that provides temporal consistency guidance but is flawed in many cases. To this end, a neural network is trained to mimic a filter to learn the consistent features (e.g., color, brightness) and avoid introducing the artifacts in the atlas. To validate our method, we construct a dataset that contains diverse real-world flickering videos. Extensive experiments show that our method achieves satisfying deflickering performance and even outperforms baselines that use extra guidance on a public benchmark.