Edge-Directed Single-Image Super-Resolution Via Adaptive Gradient Magnitude Self-Interpolation

• Published in: IEEE transactions on circuits and systems for video technology Vol. 23; no. 8; pp. 1289 - 1299
• Main Authors: Wang, Lingfeng, Xiang, Shiming, Meng, Gaofeng, Wu, Huaiyu, Pan, Chunhong
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.2013; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Computer systems; Detection, estimation, filtering, equalization, prediction; Display; Edge-directed; Electronics; Estimation; Exact sciences and technology; gradient magnitude transformation; Hardware; Image edge detection; Image reconstruction; Image resolution; Information, signal and communications theory; Interpolation; Kernel; Pattern recognition. Digital image processing. Computational geometry; Signal and communications theory; Signal, noise; super-resolution; Telecommunications and information theory; Training; Computer vision; State of the art; High resolution; Image resolution; Adaptive algorithm; Superresolution; super-resolution; Vision system; Low resolution; Direct method; Image quality; Interpolation; gradient magnitude transformation; High field; Computer system; Edge-directed; Gradient method
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2013.2240915

Super-resolution from a single image plays an important role in many computer vision systems. However, it is still a challenging task, especially in preserving local edge structures. To construct high-resolution images while preserving the sharp edges, an effective edge-directed super-resolution method is presented in this paper. An adaptive self-interpolation algorithm is first proposed to estimate a sharp high-resolution gradient field directly from the input low-resolution image. The obtained high-resolution gradient is then regarded as a gradient constraint or an edge-preserving constraint to reconstruct the high-resolution image. Extensive results have shown both qualitatively and quantitatively that the proposed method can produce convincing super-resolution images containing complex and sharp features, as compared with the other state-of-the-art super-resolution algorithms.