English

Unfolding a blurred image

Computer Vision and Pattern Recognition 2022-01-31 v1

Abstract

We present a solution for the goal of extracting a video from a single motion blurred image to sequentially reconstruct the clear views of a scene as beheld by the camera during the time of exposure. We first learn motion representation from sharp videos in an unsupervised manner through training of a convolutional recurrent video autoencoder network that performs a surrogate task of video reconstruction. Once trained, it is employed for guided training of a motion encoder for blurred images. This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder. As an intermediate step, we also design an efficient architecture that enables real-time single image deblurring and outperforms competing methods across all factors: accuracy, speed, and compactness. Experiments on real scenes and standard datasets demonstrate the superiority of our framework over the state-of-the-art and its ability to generate a plausible sequence of temporally consistent sharp frames.

Keywords

Cite

@article{arxiv.2201.12010,
  title  = {Unfolding a blurred image},
  author = {Kuldeep Purohit and Anshul Shah and A. N. Rajagopalan},
  journal= {arXiv preprint arXiv:2201.12010},
  year   = {2022}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1804.02913

R2 v1 2026-06-24T09:07:00.065Z