Context-constrained hallucination for image super-resolution

Sun, Jian; Zhu, Jiejie; Tappen, Marshall F.

doi:10.1109/cvpr.2010.5540206

Cited by 100 publications

(81 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We use two image sets as the HR ground truth data for evaluation. The first set contains 200 images from the Berkeley segmentation dataset [20], which is widely used for SISR evaluations [11,9,32,12]. All images are of 321×481 pixels covering diverse contents acquired in a professional photographic style.…”

Section: Benchmark Settingsmentioning

confidence: 99%

“…Broadly speaking, SISR algorithms can be categorized based on their tasks. While domain-specific SISR algorithms focus on specific classes of images such as faces [35,42], scenes [33], and graphics artwork [18], generic SISR algorithms [10,38,8,3,27,30,11,46,9,34,32,12,5,39,44,43] are developed for all kinds of images where the priors are typically based on primitive image properties such as edges and segments. In order to evaluate the performance of a SISR algorithm, human subject studies or ground truth images are used [33,43].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single-Image Super-Resolution: A Benchmark

Yang

2014

Lecture Notes in Computer Science

519

329

View full text Add to dashboard Cite

Abstract. Single-image super-resolution is of great importance for vision applications, and numerous algorithms have been proposed in recent years. Despite the demonstrated success, these results are often generated based on different assumptions using different datasets and metrics. In this paper, we present a systematic benchmark evaluation for state-of-the-art single-image super-resolution algorithms. In addition to quantitative evaluations based on conventional full-reference metrics, human subject studies are carried out to evaluate image quality based on visual perception. The benchmark evaluations demonstrate the performance and limitations of state-of-the-art algorithms which sheds light on future research in single-image super-resolution.

show abstract

Section: Benchmark Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Single-Image Super-Resolution: A Benchmark

Yang

2014

Lecture Notes in Computer Science

519

329

View full text Add to dashboard Cite

show abstract

“…Sun et al . [20] oversegment their input intensity image into regions of assumed similar texture and lookup an external database using descriptors computed from the regions. HaCohen et al .…”

Section: Multiple Depth Imagesmentioning

confidence: 99%

“…In the single image SR community, quantitative results have been criticized for not being representative of perceptual quality [17,18], and some authors choose to ignore them completely [19,21,20]. We first evaluated our technique on the Middlebury stereo dataset [36].…”

Section: Quantitative Evaluation Against Image Based Techniquesmentioning

confidence: 99%

Patch Based Synthesis for Single Depth Image Super-Resolution

Aodha

Campbell

Nair

et al. 2012

Computer Vision – ECCV 2012

163

196

View full text Add to dashboard Cite

Abstract. We present an algorithm to synthetically increase the resolution of a solitary depth image using only a generic database of local patches. Modern range sensors measure depths with non-Gaussian noise and at lower starting resolutions than typical visible-light cameras. While patch based approaches for upsampling intensity images continue to improve, this is the first exploration of patching for depth images. We match against the height field of each low resolution input depth patch, and search our database for a list of appropriate high resolution candidate patches. Selecting the right candidate at each location in the depth image is then posed as a Markov random field labeling problem. Our experiments also show how important further depth-specific processing, such as noise removal and correct patch normalization, dramatically improves our results. Perhaps surprisingly, even better results are achieved on a variety of real test scenes by providing our algorithm with only synthetic training depth data.

show abstract

“…Also image capturing setting is not ideal so the resulting images are blurred and noisy. Regarding that using of supper resolution techniques to enhance resolution of images and maintain the details of them is preferable [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%