# BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering

arXiv: https://arxiv.org/abs/2403.06243 · HTML: https://mlsanity.com/paper/2403.06243/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 10 Mar 2024.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2](https://mlsanity.com/paper/2112.14683/) (2021)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Layered Neural Atlases for Consistent Video Editing](https://mlsanity.com/paper/2109.11418/) (2021)
- [Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN](https://mlsanity.com/paper/1811.09245/) (2018)
- [Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN](https://mlsanity.com/paper/1904.10247/) (2019)
- [VIDM: Video Implicit Diffusion Models](https://mlsanity.com/paper/2212.00235/) (2022)
- [Blind Video Temporal Consistency via Deep Video Prior](https://mlsanity.com/paper/2010.11838/) (2020)
- [HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms](https://mlsanity.com/paper/2011.11731/) (2020)
- [MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation](https://mlsanity.com/paper/2401.04468/) (2024)
- [Bringing Old Films Back to Life](https://mlsanity.com/paper/2203.17276/) (2022)
- [Blind Video Deflickering by Neural Filtering with a Flawed Atlas](https://mlsanity.com/paper/2303.08120/) (2023)
- [Self-Supervised Learning via Conditional Motion Propagation](https://mlsanity.com/paper/1903.11412/) (2019)
- [Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation](https://mlsanity.com/paper/1908.07683/) (2019)
- [Automatic Temporally Coherent Video Colorization](https://mlsanity.com/paper/1904.09527/) (2019)
- [Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior](https://mlsanity.com/paper/2112.01766/) (2021)
- [Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising](https://mlsanity.com/paper/2101.10760/) (2021)
- [Separable Convolutional LSTMs for Faster Video Segmentation](https://mlsanity.com/paper/1907.06876/) (2019)
- [Pik-Fix: Restoring and Colorizing Old Photos](https://mlsanity.com/paper/2205.01902/) (2022)
- [Rethinking RAFT for Efficient Optical Flow](https://mlsanity.com/paper/2401.00833/) (2024)
- [Learning Long-Term Style-Preserving Blind Video Temporal Consistency](https://mlsanity.com/paper/2103.07278/) (2021)
- [LucidDream: Controlled Temporally-Consistent DeepDream on Videos](https://mlsanity.com/paper/1911.11960/) (2019)

## Abstract (arXiv)

Developing blind video deflickering (BVD) algorithms to enhance video temporal consistency, is gaining importance amid the flourish of image processing and video generation. However, the intricate nature of video data complicates the training of deep learning methods, leading to high resource consumption and instability, notably under severe lighting flicker. This underscores the critical need for a compact representation beyond pixel values to advance BVD research and applications. Inspired by the classic scale-time equalization (STE), our work introduces the histogram-assisted solution, called BlazeBVD, for high-fidelity and rapid BVD. Compared with STE, which directly corrects pixel values by temporally smoothing color histograms, BlazeBVD leverages smoothed illumination histograms within STE filtering to ease the challenge of learning temporal data using neural networks. In technique, BlazeBVD begins by condensing pixel values into illumination histograms that precisely capture flickering and local exposure variations. These histograms are then smoothed to produce singular frames set, filtered illumination maps, and exposure maps. Resorting to these deflickering priors, BlazeBVD utilizes a 2D network to restore faithful and consistent texture impacted by lighting changes or localized exposure issues. BlazeBVD also incorporates a lightweight 3D network to amend slight temporal inconsistencies, avoiding the resource consumption issue. Comprehensive experiments on synthetic, real-world and generated videos, showcase the superior qualitative and quantitative results of BlazeBVD, achieving inference speeds up to 10x faster than state-of-the-arts.