Home / Publications


International Conference on Computer Vision (ICCV 2023)

Joint Demosaicing and Deghosting of Time-Varying Exposures for Single-Shot HDR Imaging
  Jungwoo Kim Min H. Kim  
  (a) Input quad-Bayer patterned RAW image with different exposure times and colors. (b) Three multi-exposure images. (c) Our method result. We jointly solve demosaicing and deblurring problems to achieve a high-quality single-shot HDR image from the quad-Bayer pattern.  

The quad-Bayer patterned image sensor has made significant improvements in spatial resolution over recent years due to advancements in image sensor technology. This has enabled single-shot high-dynamic-range (HDR) imaging using spatially varying multiple exposures. Popular methods for multi-exposure array sensors involve varying the gain of each exposure, but this does not effectively change the photoelectronic energy in each exposure. Consequently, HDR images produced using gain-based exposure variation may suffer from noise and details being saturated. To address this problem, we intend to use time-varying exposures in quad-Bayer patterned sensors. This approach allows long-exposure pixels to receive more photon energy than short- or middle-exposure pixels, resulting in higher-quality HDR images. However, time-varying exposures are not ideal for dynamic scenes and require an additional deghosting method. To tackle this issue, we propose a single-shot HDR demosaicing method that takes time-varying multiple exposures as input and jointly solves both the demosaicing and deghosting problems. Our method uses a feature-extraction module to handle mosaiced multiple exposures and a multiscale transformer module to register spatial displacements of multiple exposures and colors. We also created a dataset of quad-Bayer sensor input with time-varying exposures and trained our network using this dataset. Results demonstrate that our method outperforms baseline HDR reconstruction methods with both synthetic and real datasets. With our method, we can achieve high-quality HDR images in challenging lighting conditions.

  ICCV 2023 presentation
   author = {Jungwoo Kim and Min H. Kim},
   title = {Joint Demosaicing and Deghosting of Time-Varying 
      Exposures for Single-Shot HDR Imaging},
   booktitle = {Proc. IEEE/CVF International Conference 
      on Computer Vision (ICCV 2023)},
   month = {October},
   year = {2023}
Preprint paper:
PDF (2.0MB)
material #1:
PDF (0.8MB)
www GitHub code &

Hosted by Visual Computing Laboratory, School of Computing, KAIST.