Blind Video Deflickering by Neural Filtering with a Flawed Atlas
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10439-10448
Abstract
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. The source code is publicly available at https://chenyanglei.github.io/deflicker.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Blind video temporal consistencyACM Transactions on Graphics, 2015
- Intrinsic images in the wildACM Transactions on Graphics, 2014
- Video Panorama for 2D to 3D ConversionComputer Graphics Forum, 2012
- Practical temporal consistency for image-based graphics applicationsACM Transactions on Graphics, 2012
- Single Image Haze Removal Using Dark Channel PriorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Stabilization of Flicker-Like Effects in Image Sequences through Local Contrast CorrectionSIAM Journal on Imaging Sciences, 2010
- Automatic Panoramic Image Stitching using Invariant FeaturesInternational Journal of Computer Vision, 2006
- Panoramic video textures2005
- Mosaic based representations of video sequences and their applications2002
- Video indexing based on mosaic representationsProceedings of the IEEE, 1998