Singlephoton Cameras Image Reconstruction Using Vision Transformer

• doi: 10.1109/CCAI57533.2023.10201259
• title: Single-Photon Cameras Image Reconstruction Using Vision Transformer
• publisher: IEEE
• isbn: 979-8-3503-3527-9
• issn:
• rank: 3575
• access_type: LOCKED
• content_type: Conferences
• abstract: Single-photon camera is a novel camera type that utilizes image sensor with photon-counting capability. Recently, the potential of such sensors to achieve high spatial resolutions (e.g., 10^9pixels/chip) and frame rates (e.g., 10^6frames/sec) is well-established. However, there is a significant difference in the output data between single-photon cameras and traditional CMOS sensor cameras. Therefore, conventional image reconstruction algorithms cannot be utilized. Vison Transformer has impressive performance on image processing tasks, and this paper will design a plug-and-play algorithm for reconstructing images from single-photon cameras and integrate image processing algorithms based on deep neural networks like ViT. The results demonstrate our methods can achieve improvement both in PSNR and SSIM.
• article_number: 10201259
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10201259
• html_url: https://ieeexplore.ieee.org/document/10201259/
• abstract_url: https://ieeexplore.ieee.org/document/10201259/
• publication_title: 2023 IEEE 3rd International Conference on Computer Communication and Artificial Intelligence (CCAI)
• conference_location: Taiyuan, China
• conference_dates: 26-28 May 2023
• publication_number: 10199106
• is_number: 10201240
• publication_year: 2023
• publication_date: 26-28 May 2023
• start_page: 296
• end_page: 300
• citing_paper_count: 1
• citing_patent_count: 0
• download_count: 268
• insert_date: 20230803
• index_terms:
  • ieee_terms:
    • Image sensors
    • Artificial neural networks
    • Cameras
    • Transformers
    • Sensors
    • Task analysis
    • Spatial resolution
  • author_terms:
    • single-photon camera
    • plug-and-play
    • image reconstruction
    • vison transformer
  • dynamic_index_terms:
    • Image Reconstruction
    • Iterative Reconstruction
    • Tomographic Reconstruction
    • Vision Transformer
    • Single-photon Cameras
    • Neural Network
    • Spatial Resolution
    • Image Processing
    • Deep Neural Network
    • Image Sensor
    • Camera Sensor
    • Reconstruction Algorithm
    • Image Processing Tasks
    • Camera Type
    • Traditional Cameras
    • Deep Learning
    • Optimization Problem
    • Convolutional Neural Network
    • Photography
    • Gaussian Noise
    • Poisson Distribution
    • Poissonian
    • Estimation Problem
    • Analog-to-digital Converter
    • Analog-to-digital
    • Digital-to-analog Converter
    • Single-photon Avalanche Diode
    • Conventional Camera
    • Single Photon
    • High Dynamic Range
    • Single Camera
    • Quantum State Tomography
    • Quantum Process Tomography
    • Quantum Image
    • Quantum Tomography
    • Markov Random Field
    • Maximum A Posteriori
    • Attention In The Field
    • Binary Bits
• isbn_formats:
  • format: Print on Demand(PoD) ISBN, value: 979-8-3503-3527-9, isbnType: New-2005
  • format: USB ISBN, value: 979-8-3503-3525-5, isbnType: New-2005
  • format: Electronic ISBN, value: 979-8-3503-3526-2, isbnType: New-2005
• authors:
  • Author Name: Xingzheng Wang
    Affiliation: Beijing Institute of Technology, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/37085533045
    ID: 37085533045
    Order: 1
    Author Affiliations:
    • Beijing Institute of Technology, Beijing, China

Image Sensor

• sensor_type: Single Photon Avalanche Diode (SPAD)
• resolution: 16.7 Megapixels
• dynamic_range: N/A
• pixel_size: N/A
• dark_current: 0.12 e- rms

Optical Data

• focal_length: N/A
• aperture: N/A
• field_of_view: N/A
• distortion: N/A

Performance Metrics

• frame_rate: 10^6 frames/sec
• signal_to_noise_ratio: N/A
• sensitivity: N/A
• shutter_speed: N/A
• power_consumption: N/A
• noise: 0.12 e-

Applications & Benefits

• cell_imaging: Used for high sensitivity low-light applications.
• benefits: High spatial resolution and frame rates suitable for various advanced imaging applications.

Supporting Organizations

• supported_by: Beijing Institute of Technology

Manuscript Details

• publication_date: 26-28 May 2023

Relevancy Score

• score: 8
• missing_fields:
  • fill factor
  • quantum efficiency
  • readout speed
  • temporal noise
  • fixed-pattern noise
  • analog-to-digital conversion techniques
  • microlenses
  • on-chip colour filters
  • global or rolling shutters
  • backside illumination

Processed JSON Filename

request_668b874e-d364-4153-b428-04473f2f3100-singlephoton_cameras_image_reconstruction_using_vision_transformer.json