Going Unconstrained With Rolling Shutter Deblurring

• doi: 10.1109/ICCV.2017.432
• title: Going Unconstrained with Rolling Shutter Deblurring
• publisher: IEEE
• isbn: 978-1-5386-1033-6
• issn: 2380-7504
• rank: 2550
• access_type: LOCKED
• content_type: Conferences
• abstract: Most present-day imaging devices are equipped with CMOS sensors. Motion blur is a common artifact in handheld cameras. Because CMOS sensors mostly employ a rolling shutter (RS), the motion deblurring problem takes on a new dimension. Although few works have recently addressed this problem, they suffer from many constraints including heavy computational cost, need for precise sensor information, and inability to deal with wide-angle systems (which most cell-phone and drone cameras are) and irregular camera trajectory. In this work, we propose a model for RS blind motion deblurring that mitigates these issues significantly. Comprehensive comparisons with state-of-the-art methods reveal that our approach not only exhibits significant computational gains and unconstrained functionality but also leads to improved deblurring performance.
• article_number: 8237694
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237694
• html_url: https://ieeexplore.ieee.org/document/8237694/
• abstract_url: https://ieeexplore.ieee.org/document/8237694/
• publication_title: 2017 IEEE International Conference on Computer Vision (ICCV)
• conference_location: Venice, Italy
• conference_dates: 22-29 Oct. 2017
• publication_number: 8234942
• is_number: 8237262
• publication_year: 2017
• publication_date: 22-29 Oct. 2017
• start_page: 4030
• end_page: 4038
• citing_paper_count: 9
• citing_patent_count: 0
• download_count: 295
• insert_date: 20171225
• index_terms:
  • ieee_terms:
    • Cameras
    • Charge coupled devices
    • Sensor systems
    • Three-dimensional displays
    • Drones
    • Semiconductor device modeling
  • dynamic_index_terms:
    • Rolling Shutter
    • Need For Information
    • Motion Blur
    • Sensor Information
    • Computational Efficiency
    • CCD Camera
    • Charge-coupled Device
    • Entire Image
    • Forward Model
    • Inertial Measurement Unit
    • Inertial Sensors
    • Real Examples
    • Maximum A Posteriori
    • Image Gradient
    • Blurred Images
    • Camera Motion
    • Shutter Speed
    • 3D Rotation
    • In-plane Rotation
    • Blur Kernel
    • Finest Level
    • Latent Image
    • Row Block
• isbn_formats:
  • format: Print on Demand(PoD) ISBN, value: 978-1-5386-1033-6, isbnType: New-2005
  • format: Electronic ISBN, value: 978-1-5386-1032-9, isbnType: New-2005
• authors:
  • Author Name: Mahesh Mohan M.R.
    Affiliation: Indian Inst. of Technol. Madras, Chennai, India
    Author URL: https://ieeexplore.ieee.org/author/37086566789
    ID: 37086566789
    Order: 1
    Author Affiliations:
    • Indian Inst. of Technol. Madras, Chennai, India
  • Author Name: A.N. Rajagopalan
    Affiliation: Indian Institute of Technology Madras, Chennai, India
    Author URL: https://ieeexplore.ieee.org/author/37274528800
    ID: 37274528800
    Order: 2
    Author Affiliations:
    • Indian Institute of Technology Madras, Chennai, India
  • Author Name: Gunasekaran Seetharaman
    Affiliation: U.S. Naval Res. Lab., Washington, PA, USA
    Author URL: https://ieeexplore.ieee.org/author/37284323900
    ID: 37284323900
    Order: 3
    Author Affiliations:
    • U.S. Naval Res. Lab., Washington, PA, USA

Image Sensor

• sensor_type: CMOS
• resolution: Not specified in the text
• dynamic_range: Not specified in the text
• pixel_size: Not specified in the text
• dark_current: Not specified in the text

Optical Data

• focal_length: 29mm (wide-angle), 50mm (narrow-angle)
• aperture: Not specified in the text
• field_of_view: Not specified in the text
• distortion: Not specified in the text

Performance Metrics

• frame_rate: Not specified in the text
• signal_to_noise_ratio: Not specified in the text
• sensitivity: Not specified in the text
• shutter_speed: te=1/1000s, 1/500s, etc.
• power_consumption: Not specified in the text
• noise: Not specified in the text

Applications & Benefits

• cell_imaging: Medical devices
• benefits: Supports a variety of applications such as smartphones, automotive systems, etc.

Supporting Organizations

• supported_by: Asian Office of Aerospace Research and Development, AOARD/AFOSR

Manuscript Details

• publication_date: 22-29 Oct. 2017

Relevancy Score

• score: 8
• 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_7528ff32-2f75-45a5-9570-832d823a29ed-going_unconstrained_with_rolling_shutter_deblurring.json