Journal
ACM TRANSACTIONS ON GRAPHICS
Volume 36, Issue 4, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3072959.3073609
Keywords
high dynamic range imaging; convolutional neural network
Categories
Funding
- ONR [N000141512013]
- NSF [1617234]
- UC San Diego Center for Visual Computing
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1617234] Funding Source: National Science Foundation
- U.S. Department of Defense (DOD) [N000141512013] Funding Source: U.S. Department of Defense (DOD)
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available