Cross-Field Joint Image Restoration via Scale Map

Yan, Qing; Shen, Xiaoyong; Liu, Xü; Zhuo, Shaojie; Zhang, Xiaopeng; Shen, Liang; Jia, Jiaya

doi:10.1109/iccv.2013.194

Cited by 119 publications

(161 citation statements)

References 24 publications

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“…9(c). This is the main difference between the proposed denoising method and the conventional image fusion methods [2,3,21,22]. From these results, it can be concluded that the proposed near-infrared coloring method is effective at removing noise of the captured visible color images in dim lighting condition.…”

Section: Detail Layer Transfermentioning

confidence: 84%

See 2 more Smart Citations

Near-Infrared Coloring via a Contrast-Preserving Mapping Model

Son

Zhang

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Section: Detail Layer Transfermentioning

confidence: 84%

“…oisy visible colo mage via the pro il layer transfer e denoised using denoised using t ap method [22].…”

Section: Detail Layer Transfermentioning

confidence: 99%

See 1 more Smart Citation

Near-Infrared Coloring via a Contrast-Preserving Mapping Model

Son

Zhang

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

“…We use RGB images and near infrared (NIR) images as multi-source images in our experiments. The database of the RGB/NIR images captured in different fields were released by The Chinese University of Hong Kong [7].…”

Section: Experimental Validationmentioning

confidence: 99%

A Hypergraph Matching Framework for Refining Multi-source Feature Correspondences

Zhang

Wang

et al. 2015

Graph-Based Representations in Pattern Recognition

View full text Add to dashboard Cite

Abstract. In this paper, we develop a hypergraph matching framework which enables feature correspondence refinement for multi-source images. For images obtained from different sources (e.g., RGB images and infrared images), we first extract feature points by using one feature extraction scheme. We then establish feature point correspondences in terms of feature similarities. In this scenario, mismatches tend to occur because the feature extraction scheme may exhibit certain ambiguity in characterizing feature similarities for multi-source images. To eliminate this ineffectiveness, we establish an association hypergraph based on the feature point correspondences, where one vertex represents a feature point pair resulted from the feature matching and one hyperedge reflects the higher-order structural similarity among feature point tuples. We then reject the mismatches by identifying outlier vertices of the hypergraph through higher order clustering. Our method is invariant to scale variation of objects because of its capability for characterizing higher order structure. Furthermore, our method is computationally more efficient than existing hypergraph matching methods because the feature matching heavily reduces the enumeration of possible point tuples for establishing hypergraph models. Experimental results show the effectiveness of our method for refining feature matching.

show abstract

“…All the dataset images used for learning and testing were the VIS and NIR image pairs captured by the RGB-NIR camera [14][15][16][17]. The training images are 20 sets of 1024 × 682 VIS / NIR images [14] taken indoors, and the images used in the test are some of the images used in [15][16][17] as shown in Fig. 6.…”

Section: A Experimental Conditionmentioning

confidence: 99%