VCLab

 
RESEARCH AREAS   PEOPLE   PUBLICATIONS   COURSES   ABOUT US
Home / Publications

indicator

International Conference on Computer Vision, Theory and Applications (VISAPP 2026)
 
Diffusion-Based HDR Reconstruction from Mosaiced Exposure Images
 
 
  Seeha Lee   Dongyoung Choi   Min H. Kim  
         
  KAIST  
         
  teaser
  (a) Input quad-Bayer patterned RAW images with varying exposure times. (b) and (c) Three multi-exposed input images. (d) and (e) Results from DiffHDR and our method, respectively. The results demonstrate that our method reconstructs fine details.  
     
     
   
  Abstract
   
  Snapshot-based HDR imaging from Bayer-patterned multi-exposure inputs has gained significant attention with recent advancements in HDR imaging technology. Learning-based approaches have enabled the reconstruction of HDR images from extremely sparse multi-exposure measurements captured on a single Bayer-patterned sensor. However, existing learning-based methods predominantly rely on tone-mapped representations due to the inherent challenges of direct supervision in the HDR radiance domain. This tone-mapping-based approach suffers from critical limitations, including amplified noise and structural distortions in the reconstructed HDR images. The fundamental challenge arises from the high dynamic range of HDR radiance values, which exhibit a sparse and uneven distribution in floating-point space, making gradient-based optimization unstable. To address these issues, we propose a novel diffusion-based HDR reconstruction framework that operates directly in a split HDR radiance domain while preserving the linearity of the original HDR radiance values. By leveraging the generative power of diffusion models, our approach effectively learns the structural and radiometric characteristics of HDR images, leading to superior detail preservation, reduced noise artifacts, and enhanced reconstruction fidelity. Experiments demonstrate that our method outperforms state-of-the-art techniques in both qualitative and quantitative evaluations.
   
  BibTeX
  
@InProceedings{Lee2:visapp:2026,
  author  = {Seeha Lee and Dongyoung Choi  and Min H. Kim},
  title   = {Diffusion-Based HDR Reconstruction from 
             Mosaiced Exposure Images},
  booktitle = {Proc. Int. Conf. Computer Vision, 
            Theory and Applications (VISAPP 2026)},
  address = {Marbella, Spain},
  year = {2026},
  pages = {},
}

   
   
icon
 Preprint paper:
PDF (4.9MB)
 

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

 KAIST