mlsanityData to 7 Oct 2026

Learning Spatially Varying Pixel Exposures for Motion Deblurring

arXiv 2204.07267 ↗First posted 14 Apr 2022eess.IV cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Computationally removing the motion blur introduced by camera shake or object motion in a captured image remains a challenging task in computational photography. Deblurring methods are often limited by the fixed global exposure time of the image capture process. The post-processing algorithm either must deblur a longer exposure that contains relatively little noise or denoise a short exposure that intentionally removes the opportunity for blur at the cost of increased noise. We present a novel approach of leveraging spatially varying pixel exposures for motion deblurring using next-generation focal-plane sensor--processors along with an end-to-end design of these exposures and a machine learning--based motion-deblurring framework. We demonstrate in simulation and a physical prototype that learned spatially varying pixel exposures (L-SVPE) can successfully deblur scenes while recovering high frequency detail. Our work illustrates the promising role that focal-plane sensor--processors can play in the future of computational imaging.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 36 of its 67 references that are in the map. First posted on arXiv 14 Apr 2022.

Builds on

36 of 67 references.

References · 36

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  6. 2021Multi-Stage Progressive Image Restorationcited by 813
  7. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  8. 2017The Perception-Distortion Tradeoffcited by 582
  9. 2018Learning to See in the Darkcited by 459
  10. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  11. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  12. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
24 more
  1. 2017Burst Denoising with Kernel Prediction Networkscited by 156
  2. 2015Learning a Convolutional Neural Network for Non-uniform Motion Blur Removalcited by 148
  3. 2020A Physics-based Noise Formation Model for Extreme Low-light Raw Denoisingcited by 138
  4. 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
  5. 2019FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimationcited by 128
  6. 2020Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurringcited by 119
  7. 2019Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Trainingcited by 112
  8. 2016A Neural Approach to Blind Motion Deblurringcited by 69
  9. 2014Learning to Deblurcited by 66
  10. 2019Deep Optics for Monocular Depth Estimation and 3D Object Detectioncited by 65
  11. 2019Deep Optics for Single-shot High-dynamic-range Imagingcited by 62
  12. 2018Learning to Extract a Video Sequence from a Single Motion-Blurred Imagecited by 56
  13. 2017Lensless computational imaging through deep learningcited by 44
  14. 2016Learning Sensor Multiplexing Design through Back-propagationcited by 28
  15. 2020FlatNet: Towards Photorealistic Scene Reconstruction from Lensless Measurementscited by 26
  16. 2016DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensingcited by 20
  17. 2019Data-Driven Design for Fourier Ptychographic Microscopycited by 18
  18. 2021Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systemscited by 15
  19. 2021HDR Video Reconstruction with Tri-Exposure Quad-Bayer Sensorscited by 13
  20. 2021MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encodingcited by 10
  21. 2019Photosequencing of Motion Blur using Short and Long Exposurescited by 9
  22. 2021Video Reconstruction from a Single Motion Blurred Image using Learned Dynamic Phase Codingcited by 5
  23. 2020AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processorscited by 4
  24. 2020Motion Deblurring using Spatiotemporal Phase Aperture Codingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 2; 2025: 4; 2026: 1.

12 papers.

  1. 2022Physics vs. Learned Priors: Rethinking Camera and Algorithm Design for Task-Specific Imagingcited by 6
  2. 2023PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensorscited by 6
  3. 2023Spatially Varying Exposure with 2-by-2 Multiplexing: Optimality and Universalitycited by 6
  4. 2022Robust Scene Inference under Noise-Blur Dual Corruptionscited by 2
  5. 2024TaCOS: Task-Specific Camera Optimization with Simulationcited by 2
  6. 2025Neural Ganglion Sensors: Learning Task-specific Event Cameras Inspired by the Neural Circuit of the Human Retinacited by 2
  7. 2025Single-shot HDR using conventional image sensor shutter functions and optical randomizationcited by 2
  8. 2022Video frame interpolation for high dynamic range sequences captured with dual-exposure sensorscited by 1
  9. 2024Non-Uniform Exposure Imaging via Neuromorphic Shutter Controlcited by 0
  10. 2025Towards Spatially-Varying Gain and Binningcited by 0
  11. 2025JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithmscited by 0
  12. 2026Generating HDR Video from SDR Videocited by 0