Deep High Dynamic Range Imaging of Dynamic Scenes

Deep High Dynamic Range Imaging of Dynamic Scenes


Nima Khademi Kalantari Ravi Ramamoorthi
University of California, San Diego University of California, San Diego


Producing a high dynamic range (HDR) image from a set of images with different exposures is a challenging process for dynamic scenes. A category of existing techniques first register the input images to a reference image and then merge the aligned images into an HDR image. However, the artifacts of the registration usually appear as ghosting and tearing in the final HDR images. In this paper, we propose a learning-based approach to address this problem for dynamic scenes. We use a convolutional neural network (CNN) as our learning model and present and compare three different system architectures to model the HDR merge process. Furthermore, we create a large dataset of input LDR images and their corresponding ground truth HDR images to train our system. We demonstrate the performance of our system by producing high-quality HDR images from a set of three LDR images. Experimental results show that our method consistently produces better results than several state-of-the-art approaches on challenging scenes.



18.6 MB

Lo-res PDF

0.8 MB

Supplementary material

331 MB

External URL

Test set

405 MB

Training set

1.95 GB

Source code

4.08 MB


    author  = {Nima Khademi Kalantari and Ravi Ramamoorthi},
    title   = {Deep High Dynamic Range Imaging of Dynamic Scenes},
    journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH 2017)},
    volume  = {36},
    number  = {4},
    year    = {2017},