MM '08 Proceedings of the 16th ACM international conference on Multimedia
Computer Vision and Image Understanding
Joint Blind Super-Resolution and Shadow Removing
IEICE - Transactions on Information and Systems
SoftCuts: a soft edge smoothness prior for color image super-resolution
IEEE Transactions on Image Processing
Locality preserving constraints for super-resolution with neighbor embedding
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
New learning based super-resolution: use of DWT and IGMRF prior
IEEE Transactions on Image Processing
New learning based super-resolution: use of DWT and IGMRF prior
IEEE Transactions on Image Processing
Colorization for single image super resolution
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Image super-resolution by vectorizing edges
MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part I
Edge-preserving color image denoising through tensor voting
Computer Vision and Image Understanding
Image super-resolution by textural context constrained visual vocabulary
Image Communication
| Hi-index | 0.00 |
Inspired by multi-scale tensor voting, a computational framework for perceptual grouping and segmentation, we propose an edge-directed technique for color image superresolution given a single low-resolution color image. Our multi-scale technique combines the advantages of edgedirected, reconstruction-based and learning-based methods, and is unique in two ways. First, we consider simultaneously all the three color channels in our multi-scale tensor voting framework to produce a multi-scale edge representation to guide the process of high-resolution color image reconstruction, which is subject to the back projection constraint. Fine details are inferred without noticeable blurry or ringing artifacts. Second, the inference of highresolution curves is achieved by multi-scale tensor voting, using the dense voting field as an edge-preserving smoothness prior which is derived geometrically without any timeconsuming learning procedure. Qualitative and quantitative results indicate that our method produces convincing results in complex test cases typically used by state-of-theart image super-resolution techniques.