Image hallucination with primal sketch priors

We propose a Bayesian approach to image hallucination. Given a generic low resolution image, we hallucinate a high resolution image using a set of training images. Our work is inspired by recent progress on natural image statistics that the priors of image primitives can be well represented by examples. Specifically, primal sketch priors (e.g., edges, ridges and corners) are constructed and used to enhance the quality of the hallucinated high resolution image. Moreover, a contour smoothness constraint enforces consistency of primitives in the hallucinated image by a Markov-chain based inference algorithm. A reconstruction constraint is also applied to further improve the quality of the hallucinated image. Experiments demonstrate that our approach can hallucinate high quality super-resolution images.

[1]  R. Weale.  Vision. A Computational Investigation Into the Human Representation and Processing of Visual Information. David Marr , 1983 .

[2]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[3]  Jitendra Malik,et al.  Detecting and localizing edges composed of steps, peaks and roofs , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[4]  Michal Irani,et al.  Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency , 1993, J. Vis. Commun. Image Represent..

[5]  D. Mumford.  Perception as Bayesian Inference: Pattern theory: A unifying perspective , 1996 .

[6]  D. Mumford.  Pattern theory: a unifying perspective , 1996 .

[7]  Ping Wah Wong,et al.  Edge-directed interpolation , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[8]  J. V. van Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[9]  Sunil Arya,et al.  ANN: library for approximate nearest neighbor searching , 1998 .

[10]  J. H. Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998 .

[11]  Takeo Kanade,et al.  Limits on super-resolution and how to break them , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[12]  Michael T. Orchard,et al.  New edge directed interpolation , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[13]  Bryan S. Morse,et al.  Image magnification using level-set reconstruction , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  M. Orchard,et al.  New edge-directed interpolation , 2001, IEEE Trans. Image Process..

[15]  Harry Shum,et al.  A two-step approach to hallucinating faces: global parametric model and local nonparametric model , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  David Salesin,et al.  Image Analogies , 2001, SIGGRAPH.

[17]  Ann B. Lee,et al.  The Complex Statistics of High-Contrast Patches in Natural Images , 2001 .

[18]  William T. Freeman,et al.  Learning Low-Level Vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.