• Corpus ID: 3806811

Selective Image Super-Resolution

  title={Selective Image Super-Resolution},
  author={Ju Sun and Qiang Chen and Shuicheng Yan and Loong Fah Cheong},
In this paper we propose a vision system that performs image Super Resolution (SR) with selectivity. Conventional SR techniques, either by multi-image fusion or example-based construction, have failed to capitalize on the intrinsic structural and semantic context in the image, and performed \blind" resolution recovery to the entire image area. By comparison, we advocate examplebased selective SR whereby selectivity is exemplied in three aspects: region selectivity (SR only at object regions… 

Figures from this paper

Selective Super-Resolution for Scene Text Images
This paper proposes the use of Super-Resolution Convolutional Neural Networks (SRCNN) which are constructed to tackle issues associated with characters and text and demonstrates that standard SRCNNs trained for general object super-resolution is not sufficient and that the proposed method is a viable method in creating a robust model for text.
Landmark Image Super-Resolution by Retrieving Web Images
Experimental results demonstrate that the proposed new super-resolution (SR) scheme achieves significant improvement compared with four state-of-the-art schemes in terms of both subjective and objective qualities.
Retrieval Compensated Group Structured Sparsity for Image Super-Resolution
A group-structured sparse representation approach to make full use of both internal and external dependencies to facilitate image super-resolution and provides the desired over-completeness property when sparsely coding a given LR patch.
Joint Learning for Single-Image Super-Resolution via a Coupled Constraint
A joint learning technique is applied to train two projection matrices simultaneously and to map the original LR and HR feature spaces onto a unified feature subspace to overcome or at least to reduce the problem for NE-based SR reconstruction.
A Single Image Super Resolution Using Advanced Neighbor Embedding
An advanced Neighbor Embedding based method for Super resolution used in which combine learning technique used to train two projection matrices simultaneously and to map the original Low Resolution and High Resolution feature spaces onto a unified feature subspace.
Advance Neighbor Embedding for Image Super Resolution
The Advance Neighbor embedding (ANE) method for image super resolution gives better resolution than NE method using combine learning technique used to train two projection matrices simultaneously and to map the original Low Resolution and High Resolution feature spaces onto a unified feature subspace.


Super-resolution through neighbor embedding
  • Hong Chang, D. Yeung, Yimin Xiong
  • Computer Science, Mathematics
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
This paper proposes a novel method for solving single-image super-resolution problems, given a low-resolution image as input, and recovers its high-resolution counterpart using a set of training examples, inspired by recent manifold teaming methods.
Image super-resolution as sparse representation of raw image patches
It is shown that a small set of randomly chosen raw patches from training images of similar statistical nature to the input image generally serve as a good dictionary, in the sense that the computed representation is sparse and the recovered high-resolution image is competitive or even superior in quality to images produced by other SR methods.
Super-resolution image reconstruction: a technical overview
The goal of this article is to introduce the concept of SR algorithms to readers who are unfamiliar with this area and to provide a review for experts to present the technical review of various existing SR methodologies which are often employed.
Learning Low-Level Vision
A learning-based method for low-level vision problems—estimating scenes from images with Bayesian belief propagation, applied to the “super-resolution” problem (estimating high frequency details from a low-resolution image), showing good results.
Discriminative learned dictionaries for local image analysis
This article proposes an energy formulation with both sparse reconstruction and class discrimination components, jointly optimized during dictionary learning, for local image discrimination tasks, and paves the way for a novel scene analysis and recognition framework based on simultaneously learning discriminative and reconstructive dictionaries.
Recognition using regions
This paper presents a unified framework for object detection, segmentation, and classification using regions using a generalized Hough voting scheme to generate hypotheses of object locations, scales and support, followed by a verification classifier and a constrained segmenter on each hypothesis.
Example-Based Super-Resolution
This work built on another training-based super- resolution algorithm and developed a faster and simpler algorithm for one-pass super-resolution that requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data.
Image Superresolution Using Support Vector Regression
Investigation of the relevancy of SVR to superresolution proceeds with the possibility of using a single and general support vector regression for all image content, and the results are impressive for small training sets.
Combining efficient object localization and image classification
An efficient two stage sliding window object localization method that combines the efficiency of a linear classifier with the robustness of a sophisticated non-linear one and shows that classification can improve detection and vice versa is presented.
A closed-form solution to natural image matting, Pattern Analysis and Machine Intelligence
  • IEEE Transactions on
  • 2008