Published on Mon Sep 18 2017

Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence

Haesol Park, Kyoung Mu Lee

Conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure. We propose a pioneering unified framework that solves four problems simultaneously.

0
0
0
Abstract

The conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure. The off-the-shelf deblurring or super-resolution methods may show visually pleasing results. However, applying each technique independently before matching is generally unprofitable because this naive series of procedures ignores the consistency between images. In this paper, we propose a pioneering unified framework that solves four problems simultaneously, namely, dense depth reconstruction, camera pose estimation, super-resolution, and deblurring. By reflecting a physical imaging process, we formulate a cost minimization problem and solve it using an alternating optimization technique. The experimental results on both synthetic and real videos show high-quality depth maps derived from severely degraded images that contrast the failures of naive multi-view stereo methods. Our proposed method also produces outstanding deblurred and super-resolved images unlike the independent application or combination of conventional video deblurring, super-resolution methods.

Thu Jul 28 2016
Computer Vision
Stereo Video Deblurring
Videos acquired in low-light conditions often exhibit motion blur. This is not only visually unpleasing, but can hamper further processing. With this paper we are the first to show how the availability of stereo video can aid the challenging video deblurring task.
0
0
0
Fri Mar 01 2019
Computer Vision
Single Image Deblurring and Camera Motion Estimation with Depth Map
Camera shake during exposure is a major problem in hand-held photography. Few existing methods could handle the real 6 DoF camera motion. We propose to jointly estimate the camera motion and remove the non-uniform blur.
0
0
0
Sun Feb 03 2013
Computer Vision
Correcting Camera Shake by Incremental Sparse Approximation
The problem of deblurring an image when the blur kernel is unknown remains challenging after decades of work. We propose a new blind deconvolution method using incremental sparse edge approximation to recover images blurred by camera shake.
0
0
0
Sun Apr 07 2019
Computer Vision
Planar Geometry and Latest Scene Recovery from a Single Motion Blurred Image
Existing works on motion deblurring either ignore the effects of depth-dependent blur or work with the assumption of a multi-layered scene. We propose a first-of-its-kind approach to recover the planar geometry and latent image of the scene.
0
0
0
Thu Sep 17 2015
Computer Vision
Hand-held Video Deblurring via Efficient Fourier Aggregation
The method is motivated from the physiological fact that camera shake blur has a random nature and therefore, nearby video frames are generally blurred differently. The proposed algorithm achieves state-of-the-art results while at the same time being much faster than competitors.
0
0
0
Wed Sep 24 2014
Computer Vision
Recent Progress in Image Deblurring
This paper comprehensively reviews the recent development of image deblurring techniques. It includes non-blind/blind, spatially invariant/variant deblurring techniques. These techniques share the same objective of inferring a sharp image from a blurry image.
0
0
0