Evsassisted Joint Deblurring Rollingshutter Correction And Video Frame
Interpolation Through Sensor Inverse Modeling
- doi: 10.1109/CVPR52733.2024.02378
-
title: EVS-Assisted Joint Deblurring, Rolling-Shutter
Correction and Video Frame Interpolation Through Sensor Inverse Modeling
- publisher: IEEE
- isbn: 979-8-3503-5301-3
- issn: 1063-6919
- rank: 2340
- access_type: LOCKED
- content_type: Conferences
-
abstract: Event-based Vision Sensors (EVS) gain
popularity in en-hancing CMOS Image Sensor (CIS) video capture.
Nonide-alities of EVS such as pixel or readout latency can significantly
influence the quality of the enhanced images and warrant dedicated
consideration in the design of fusion algorithms. A novel approach for
jointly computing de-blurred, rolling-shutter artifact corrected
high-speed videos with frame rates up to 10000 FPS using inherently
blurry rolling shutter CIS frames of 120 FPS to 150 FPS in conjunction
with EVS data from a hybrid CIS-EVS sensor is presented. EVS pixel
latency, readout latency and the sensor's refractory period are
explicitly incorporated into the measurement model. This inverse
function problem is solved on a per-pixel manner using an
optimization-based framework. The interpolated images are subsequently
processed by a novel refinement network. The proposed method is
evaluated using simulated and measured datasets, under natural and
controlled environments. Extensive experiments show reduced shadowing
effect, a 4 dB increment in PSNR, and a 12 % improvement in LPIPS score
compared to state-of-the-art methods.
- article_number: 10656189
-
pdf_url:
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10656189
-
html_url:
https://ieeexplore.ieee.org/document/10656189/
-
abstract_url:
https://ieeexplore.ieee.org/document/10656189/
-
publication_title: 2024 IEEE/CVF Conference on Computer
Vision and Pattern Recognition (CVPR)
- conference_location: Seattle, WA, USA
- conference_dates: 16-22 June 2024
- publication_number: 10654794
- is_number: 10654797
- publication_year: 2024
- publication_date: 16-22 June 2024
- start_page: 25172
- end_page: 25181
- citing_paper_count: 1
- citing_patent_count: 0
- download_count: 103
- insert_date: 20240916
-
index_terms:
-
ieee_terms:
- Image quality
- Interpolation
- Computer vision
- Inverse problems
- Vision sensors
- Pattern recognition
- Optimization
-
author_terms:
- Event Camera
- Deblurring
- Rolling-Shutter Correction
- Video Frame Interpolation
-
dynamic_index_terms:
- Inverse Model
- Deblurring
- Frame Interpolation
- Video Interpolation
- Video Frame Interpolation
- Frame Rate
- Environmental Control
- Inverse Problem
- Forward Problem
- Peak Signal-to-noise Ratio
- PSNR
- Video Capture
- Refractory Period
- Refinement Network
- Rolling Shutter
- Image Quality
- Low-pass
- Low-pass Filter
- Basketball
- Nonlinear Programming
- Nonlinear Optimization
- Straightforward Way
- Photocurrent
- Explicit Model
- Spatial Attention
- Optical Flow
- Graph Optimization
- Improve Image Quality
- Measurement Equation
- Hybrid Sensor
- Delay Compensation
- Fast Motion
- Ground Truth Image
- Indoor Scenarios
- Trigger Threshold
- Perceptual Loss
-
isbn_formats:
-
format: Print on Demand(PoD) ISBN,
value: 979-8-3503-5301-3,
isbnType: New-2005
-
format: Electronic ISBN,
value: 979-8-3503-5300-6,
isbnType: New-2005
-
authors:
Image Sensor
- sensor_type: CIS-EVS hybrid sensor
- resolution: 15-MPixel CIS + 1-Mpixel EVS
- dynamic_range: 120 dB
- pixel_size: 0.18 µm
- dark_current: characterized in measurements
Optical Data
- focal_length: not specified
- aperture: not specified
- field_of_view: not specified
- distortion: not specified
Performance Metrics
- frame_rate: up to 10,000 FPS
- shutter_speed: 120-150 FPS for CIS
-
noise: specified by factors such as readout latency and
pixel latency
Applications & Benefits
-
cell_imaging: enables applications in medical and
imaging fields
-
benefits: enhanced imaging quality and reduced
artifacts through effective deblurring and frame interpolation
Supporting Organizations
Manuscript Details
- publication_date: 16-22 June 2024
Relevancy Score
- score: 9
-
missing_fields:
- focal_length
- aperture
- field_of_view
- distortion
- signal_to_noise_ratio
- sensitivity
- power_consumption
Processed JSON Filename
request_13c7e069-8045-4afd-8c77-f69a50b20122-evsassisted_joint_deblurring_rollingshutter_correction_and_video_frame_interpolation_through_sensor_inverse_modeling.json