Deep Video Deblurring: The Devil is in the Details

09/26/2019
by   Jochen Gast, et al.
33

Video deblurring for hand-held cameras is a challenging task, since the underlying blur is caused by both camera shake and object motion. State-of-the-art deep networks exploit temporal information from neighboring frames, either by means of spatio-temporal transformers or by recurrent architectures. In contrast to these involved models, we found that a simple baseline CNN can perform astonishingly well when particular care is taken w.r.t. the details of model and training procedure. To that end, we conduct a comprehensive study regarding these crucial details, uncovering extreme differences in quantitative and qualitative performance. Exploiting these details allows us to boost the architecture and training procedure of a simple baseline CNN by a staggering 3.15dB, such that it becomes highly competitive w.r.t. cutting-edge networks. This raises the question whether the reported accuracy difference between models is always due to technical contributions or also subject to such orthogonal, but crucial details.

READ FULL TEXT

page 3

page 4

page 5

page 6

page 8

research
03/28/2018

Adversarial Spatio-Temporal Learning for Video Deblurring

Camera shake or target movement often leads to undesired blur effects in...
research
11/03/2017

Convolutional Drift Networks for Video Classification

Analyzing spatio-temporal data like video is a challenging task that req...
research
12/16/2021

Spatio-Temporal CNN baseline method for the Sports Video Task of MediaEval 2021 benchmark

This paper presents the baseline method proposed for the Sports Video ta...
research
04/11/2017

Online Video Deblurring via Dynamic Temporal Blending Network

State-of-the-art video deblurring methods are capable of removing non-un...
research
03/25/2020

Prior-enlightened and Motion-robust Video Deblurring

Various blur distortions in video will cause negative impact on both hum...
research
04/04/2020

Multi-Variate Temporal GAN for Large Scale Video Generation

In this paper, we present a network architecture for video generation th...
research
06/15/2021

Cascading Convolutional Temporal Colour Constancy

Computational Colour Constancy (CCC) consists of estimating the colour o...

Please sign up or login with your details

Forgot password? Click here to reset