Deep Joint Image Filtering
ECCV 2016

1Univerisity of California, Merced       2University of Illinois, Urbana-Champaign

Joint image filters can leverage the guidance image as a prior and transfer the structural details from the guidance image to the target image for suppressing noise or enhancing spatial resolution. Existing methods rely on various kinds of explicit filter construction or hand-designed objective functions. It is thus difficult to understand, improve, and accelerate them in a coherent framework. In this paper, we propose a learning-based approach to construct a joint filter based on Convolutional Neural Networks. In contrast to existing methods that consider only the guidance image, our method can selectively transfer salient structures that are consistent in both guidance and target images. We show that the model trained on a certain type of data, e.g., RGB and depth images, generalizes well for other modalities, e.g., Flash/Non-Flash and RGB/NIR images. We validate the effectiveness of the proposed joint filter through extensive comparisons with state-of-the-art methods.


Upsampling results on NYU v2 dataset
[MRF] [GF] [JBU] [Park] [TGV] [Ham] [Ours]

    author = {Li, Yijun and Huang, Jia-Bin and Ahuja Narendra and Yang, Ming-Hsuan},
    title = {Deep Joint Image Filtering},
    booktitle = {European Conference on Computer Vision},
    year = {2016}