Blind Video Deflickering by Neural Filtering with a Flawed Atlas

TL;DR

This paper introduces a blind video deflickering method that uses neural filtering and a neural atlas to remove flickering artifacts from videos without requiring additional guidance or annotations.

Contribution

The work presents a novel blind deflickering framework leveraging neural atlas and filtering, capable of handling diverse real-world flickering videos without extra guidance.

Findings

Outperforms baseline methods on public benchmarks

Effective on diverse real-world flickering videos

Achieves satisfying deflickering performance

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.