Rolling Shutter Motion Deblurring

• doi: 10.1109/CVPR.2015.7298760
• title: Rolling shutter motion deblurring
• publisher: IEEE
• isbn: 978-1-4673-6963-3
• issn: 1063-6919
• rank: 3478
• access_type: LOCKED
• content_type: Conferences
• abstract: Although motion blur and rolling shutter deformations are closely coupled artifacts in images taken with CMOS image sensors, the two phenomena have so far mostly been treated separately, with deblurring algorithms being unable to handle rolling shutter wobble, and rolling shutter algorithms being incapable of dealing with motion blur. We propose an approach that delivers sharp and undistorted output given a single rolling shutter motion blurred image. The key to achieving this is a global modeling of the camera motion trajectory, which enables each scanline of the image to be deblurred with the corresponding motion segment. We show the results of the proposed framework through experiments on synthetic and real data.
• article_number: 7298760
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298760
• html_url: https://ieeexplore.ieee.org/document/7298760/
• abstract_url: https://ieeexplore.ieee.org/document/7298760/
• publication_title: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• conference_location: Boston, MA, USA
• conference_dates: 7-12 June 2015
• publication_number: 7293313
• is_number: 7298593
• publication_year: 2015
• publication_date: 7-12 June 2015
• start_page: 1529
• end_page: 1537
• citing_paper_count: 43
• citing_patent_count: 0
• download_count: 440
• insert_date: 20151015
• index_terms:
  • ieee_terms:
    • Cameras
    • Kernel
    • Trajectory
    • Image segmentation
    • Motion segmentation
    • Estimation
    • Polynomials
  • dynamic_index_terms:
    • Rolling Shutter
    • Image Sensor
    • Camera Sensor
    • Line Scan
    • Motion Trajectory
    • Motion Blur
    • Camera Motion
    • Exposure Time
    • Single Image
    • Focal Length
    • Focal Distance
    • Polynomial Regression
    • Polynomial Fitting
    • Time Stamp
    • Synthetic Images
    • Trajectory Model
    • Maximum A Posteriori
    • Geometric Distortion
    • Kernel Estimation
    • Epanechnikov
    • Kernel Approximation
    • Global Motion
    • Camera Pose
    • 3D Pose
    • Gauss-Newton Method
    • Gauss-Newton Algorithm
    • Latent Image
    • Blur Kernel
    • In-plane Rotation
    • Trajectory Segments
    • Blind Deconvolution
    • Global Trajectory
• isbn_formats:
  • format: USB ISBN, value: 978-1-4673-6963-3, isbnType: New-2005
  • format: Electronic ISBN, value: 978-1-4673-6964-0, isbnType: New-2005
• authors:
  • Author Name: Shuochen Su
    Affiliation: KAUST
    Author URL: https://ieeexplore.ieee.org/author/37075597500
    ID: 37075597500
    Order: 1
    Author Affiliations:
    • KAUST
    • University of British Columbia
  • Author Name: Wolfgang Heidrich
    Affiliation: KAUST
    Author URL: https://ieeexplore.ieee.org/author/37269011000
    ID: 37269011000
    Order: 2
    Author Affiliations:
    • KAUST
    • University of British Columbia

Image Sensor

• sensor_type: CMOS
• resolution: Not specified
• dynamic_range: Not specified
• pixel_size: Not specified
• dark_current: Not specified

Optical Data

• focal_length: Not specified
• aperture: Not specified
• field_of_view: Not specified
• distortion: Not specified

Performance Metrics

• shutter_speed: 1/50s

Applications & Benefits

• cell_imaging: Applicable in medical devices for imaging cells and tissues.
• benefits: Digital imaging for smartphones, medical devices, automotive systems.

Supporting Organizations

• supported_by: University of British Columbia, KAUST

Manuscript Details

• publication_date: 7-12 June 2015

Relevancy Score

• score: 9
• missing_fields:
  • resolution
  • dynamic_range
  • pixel_size
  • dark_current
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • frame_rate
  • signal_to_noise_ratio
  • sensitivity
  • power_consumption
  • noise

Processed JSON Filename

request_0971c3ef-fc39-4190-9aec-80119c112489-rolling_shutter_motion_deblurring.json