English

Blind Video Temporal Consistency via Deep Video Prior

Computer Vision and Pattern Recognition 2020-10-23 v1

Abstract

Applying image processing algorithms independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our method is only trained on a pair of original and processed videos directly instead of a large dataset. Unlike most previous methods that enforce temporal consistency with optical flow, we show that temporal consistency can be achieved by training a convolutional network on a video with the Deep Video Prior. Moreover, a carefully designed iteratively reweighted training strategy is proposed to address the challenging multimodal inconsistency problem. We demonstrate the effectiveness of our approach on 7 computer vision tasks on videos. Extensive quantitative and perceptual experiments show that our approach obtains superior performance than state-of-the-art methods on blind video temporal consistency. Our source codes are publicly available at github.com/ChenyangLEI/deep-video-prior.

Keywords

Cite

@article{arxiv.2010.11838,
  title  = {Blind Video Temporal Consistency via Deep Video Prior},
  author = {Chenyang Lei and Yazhou Xing and Qifeng Chen},
  journal= {arXiv preprint arXiv:2010.11838},
  year   = {2020}
}

Comments

NeurIPS 2020; github link: github.com/ChenyangLEI/deep-video-prior

R2 v1 2026-06-23T19:33:44.869Z