Partially Supervised Neighbor Embedding for Example-Based Image Super-Resolution

Zhang, Kaibing; Gao, Xinbo; Li, Xuelong; Tao, Dacheng

doi:10.1109/jstsp.2010.2048606

Cited by 108 publications

(51 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, the use of division into multiple sub-problems becomes important 4 Due to the limitation of space, we only performed a comparison between our method and state-of-the-art methods in [61], [62] and [64]. Examples of SR obtained by our method and the methods in [54], [57], [58], [60], [61], [62] and [64] are shown in the supplemental materials.…”

Section: B Results Of Super-resolutionmentioning

confidence: 99%

“…Furthermore, more accurate SR methods have been realized by adopting multiple nonlinear eigenspaces [53], [54], and they enable selection of the optimal subspaces. In recent years, sparse representationbased methods [9], [55], [56] and neighboring embeddingbased methods [57] have achieved successful generation of optimal subspaces for estimating missing high-frequency components. The above-mentioned methods are small parts of recent studies, and a number of new methods based on different ideas have also been proposed [58]- [60].…”

Section: ) Super-resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Subspace-Based Inverse Projections via Division Into Multiple Sub-Problems for Missing Image Data Restoration

Ogawa

Haseyama

2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-This paper presents adaptive subspace-based inverse projections via division into multiple sub-problems (ASIP-DIMS) for missing image data restoration. In the proposed method, a target problem for estimating missing image data is divided into multiple sub-problems, and each sub-problem is iteratively solved with constraints of other known image data. By projection into a subspace model of image patches, the solution of each subproblem is calculated, where we call this procedure "subspacebased inverse projection" for simplicity. The proposed method can use higher-dimensional subspaces for finding unique solutions in each sub-problem, and successful restoration becomes feasible since a high level of image representation performance can be preserved. This is the biggest contribution of this paper. Furthermore, the proposed method generates several subspaces from known training examples and enables derivation of a new criterion in the above framework to adaptively select the optimal subspace for each target patch. In this way, the proposed method realizes missing image data restoration using ASIP-DIMS. Since our method can estimate any kind of missing image data, its potential in two image restoration tasks, image inpainting and super-resolution, based on several methods for multivariate analysis is also shown in this paper.

show abstract

Section: B Results Of Super-resolutionmentioning

confidence: 99%

Section: ) Super-resolutionmentioning

confidence: 99%

Adaptive Subspace-Based Inverse Projections via Division Into Multiple Sub-Problems for Missing Image Data Restoration

Ogawa

Haseyama

2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…They also effectively reduced the dictionary size by limiting the coverage of the algorithm to the primitive areas, such as edges and corner points in the input image. Zhang et al [11] proposed an improved version of Fan and Yeung's neighbor-embedding method where some errors during HF synthesis are reduced by employing a clustering approach.…”

Section: Introductionmentioning

confidence: 99%

A Single Image Super-Resolution Algorithm Using Non-Local-Mean Self-Similarity and Noise-Robust Saliency Map

Lee

Choi

Lim

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY This paper presents a single image super-resolution (SR) algorithm based on self-similarity using non-local-mean (NLM) metric. In order to accurately find the best self-example even under noisy environment, NLM weight is employed as a self-similarity metric. Also, a pixelwise soft-switching is presented to overcome an inherent drawback of conventional self-example-based SR that it seldom works for texture areas. For the pixel-wise soft-switching, an edge-oriented saliency map is generated for each input image. Here, we derived the saliency map which can be robust against noises by using a specific training. The proposed algorithm works as follows: First, auxiliary images for an input low-resolution (LR) image are generated. Second, self-examples for each LR patch are found from the auxiliary images on a block basis, and the best match in terms of self-similarity is found as the best self-example. Third, a preliminary high-resolution (HR) image is synthesized using all the self-examples. Next, an edge map and a saliency map are generated from the input LR image, and pixel-wise weights for soft-switching of the next step are computed from those maps. Finally, a super-resolved HR image is produced by soft-switching between the preliminary HR image for edges and a linearly interpolated image for non-edges. Experimental results show that the proposed algorithm outperforms state-of-the-art SR algorithms qualitatively and quantitatively.

show abstract

“…보간 기반 초고해상도 기법 은 영상의 공간적인 연속성에 기반을 두고 저 해상도 영상의 화소 사이를 선형 보간 방법으로 보간하거나 경 계 영역 (Edge)의 방향성을 고려하여 비선형 방법으로 보간한다 [4][5][6][7][8][9] . [10][11][12][13][14] . Freeman [10] 은 고 해상도 다.…”

unclassified

“…Freeman [10] 은 고 해상도 다. Sun [13] 은 예제 기반 초고해상도 기법을 적용하는 영 역을 경계 영역 또는 특징점 등과 같이 고 해상도와 저 해상도 영상간의 대응관계가 명확한 원시 (Primitive) 영역으로 제한하여 사전의 크기를 줄임과 동시에 성능 을 확보하려 하였고, Fan 과 Yeung [11] 은 원시 영역에 대해 neighbor embedding 방법을 통해 고해상도 영상 신호를 복원함으로써 사전의 크기를 더욱 줄일 수 있는 가능성을 제시 하였으며, Zhang [14] 은 클러스터링 방법 을 접목하여 고 해상도 영상 합성 오류를 줄일 수 있도 록 Fan [11] 의 neighbor embedding 방법을 개선하였다. …”

unclassified

Super-resolution Algorithm using Local Structure Analysis and Scene Adaptive Dictionary

Choi¹,

Lim²,

Song³

2013

Journal of the Institute of Electronics Engineers of Korea

View full text Add to dashboard Cite

This paper proposes a new super-resolution algorithm where sharpness enhancement is merged in order to improve overall visual quality of up-scaled images. In the learning stage, multiple dictionaries are generated according to sharpness strength, and a proper dictionary among those dictionaries is selected to adapt to each patch in the inference stage. Also, additional post-processing suppresses boosting of artifacts in input low-resolution images during the inference stage. Experimental results that the proposed algorithm provides 0.3 higher CPBD than the bi-cubic and 0.1 higher CPBD than Song's and Fan's algorithms. Also, we can observe that the proposed algorithm shows better quality in textures and edges than the previous works. Finally, the proposed algorithm has a merit in terms of computational complexity because it requires the memory of only 17% in comparison with the previous work.

show abstract

Partially Supervised Neighbor Embedding for Example-Based Image Super-Resolution

Cited by 108 publications

References 32 publications

Adaptive Subspace-Based Inverse Projections via Division Into Multiple Sub-Problems for Missing Image Data Restoration

Adaptive Subspace-Based Inverse Projections via Division Into Multiple Sub-Problems for Missing Image Data Restoration

A Single Image Super-Resolution Algorithm Using Non-Local-Mean Self-Similarity and Noise-Robust Saliency Map

Super-resolution Algorithm using Local Structure Analysis and Scene Adaptive Dictionary

Contact Info

Product

Resources

About