Multi-image super-resolution using a locally adaptive denoising-based refinement

Bätz, Michel; Koloda, Jan; Eichenseer, Andrea; Kaup, André

doi:10.1109/mmsp.2016.7813343

Cited by 7 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For MFSR, we study interpolation, reconstruction, and deep learning methods. Interpolation MFSR comprises non-uniform interpolation (NUISR) [74], NUISR with outlier weighting (WNUISR) [18], and denoising-based refinement (DBRSR) [75]. The reconstruction methods are non-blind L 1 norm minimization with bilateral total variation prior (L1BTV) [22], bilateral edge preserving prior (BEPSR), and iteratively reweighted minimization (IRWSR) [23].…”

Section: Evaluated Algorithmsmentioning

confidence: 99%

“…For SISR, we study dictionary and deep learning methods. The dictionary methods are example-based ridge regression (EBSR) [9], sparse coding (ScSR) [77], Naive Bayes SR Interpolation BICUBIC NUISR [74], WNUISR [18] DBRSR [75] Non-blind L1BTV [22], BEPSR [78] reconstruction IRWSR [23] Blind reconstruction BVSR [24], SRB [62] forests (NBSRF) [10], and adjusted anchored neighborhood regression (A+) [12]. The deep learning methods comprise CNNs (SRCNN) [13], very deep networks (VDSR) [14], and deeply-recursive networks (DRCN) [15].…”

Section: Evaluated Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data

Köhler

Bätz

Naderi

et al. 2019

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Capturing ground truth data to benchmark super-resolution (SR) is challenging. Therefore, current quantitative studies are mainly evaluated on simulated data artificially sampled from ground truth images. We argue that such evaluations overestimate the actual performance of SR methods compared to their behavior on real images. Toward bridging this simulated-to-real gap, we introduce the Super-Resolution Erlangen (SupER) database, the first comprehensive laboratory SR database of all-real acquisitions with pixel-wise ground truth. It consists of more than 80k images of 14 scenes combining different facets: CMOS sensor noise, real sampling at four resolution levels, nine scene motion types, two photometric conditions, and lossy video coding at five levels. As such, the database exceeds existing benchmarks by an order of magnitude in quality and quantity. This paper also benchmarks 19 popular single-image and multi-frame algorithms on our data. The benchmark comprises a quantitative study by exploiting ground truth data and qualitative evaluations in a large-scale observer study. We also rigorously investigate agreements between both evaluations from a statistical perspective. One interesting result is that top-performing methods on simulated data may be surpassed by others on real data. Our insights can spur further algorithm development, and the publicy available dataset can foster future evaluations.

show abstract

Section: Evaluated Algorithmsmentioning

confidence: 99%

Section: Evaluated Algorithmsmentioning

confidence: 99%

Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data

Köhler

Bätz

Naderi

et al. 2019

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…where D i is the reconstructed multilevel texture detail information, i refers to the range of samples of D i , α controls the amount of detail boosting, β controls the high-frequency range compression, and sign is better known as signum function. The value of α typically varies in a small range (1,10], The function has the task of boosting the texture detail of the image and of suppressing the reconstruction image oversaturation. We set function f equal to 1 − e −2D i α /1 + e −2D i α , where f belongs to the hyperbolic tangent function and is a sigmoid function.…”

Section: Detail Boosting and Fusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Super-resolution (SR) reconstruction is the technology of obtaining high-resolution (HR) images or sequences from one or more low-resolution (LR) observation images by means of signal processing [1]. SR reconstruction is widely used in remote sensing, video surveillance, medical diagnosis, military [1]. SR reconstruction is widely used in remote sensing, video surveillance, medical diagnosis, military reconnaissance, and other civil and military fields [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Super-Resolution Reconstruction and Its Application Based on Multilevel Main Structure and Detail Boosting

et al. 2018

View full text Add to dashboard Cite

Vivid main structure and rich texture detail are important factors with which to determine the quality of high-resolution images after super-resolution (SR) reconstruction. Owing to the loss of high-frequency information in the process of SR reconstruction and the limitation of the accurate estimation of the unknown information in the inversion process, a gap still exists between the high-resolution image and the real image. The main structure can better preserve the edge structure of the image, and detail boosting can compensate for the missing high-frequency information in the reconstruction process. Therefore, a novel single remote-sensing image SR reconstruction method based on multilevel main structure and detail boosting (MMSDB-SR) is put forward in this paper. First, the multilevel main structure was obtained based on the decomposition of the remote-sensing image through use of the relative total variation model. Subsequently, multilevel texture detail information was obtained by a difference process. Second, the multilevel main structure and texture detail were reconstructed separately. The detail-boosting function was used to compensate for the missing high-frequency details in the reconstruction process. Finally, the high-resolution remote-sensing image with clear edge and rich texture detail can be obtained by fusing the multilevel main structure and texture-detail information. The experimental results show that the reconstructed high-resolution image has high clarity, high fidelity, and multi-detail visual effects, and the objective evaluation index exhibits significant improvement. Actual results show an average gain in entropy of up to 0.34 dB for an up-scaling of 2. Real results show an average gain in enhancement measure evaluation of up to 2.42 for an up-scaling of 2. The robustness and universality of the proposed SR method are verified.

show abstract

Spatio-Temporal Super-Resolution Reconstruction of Remote Sensing Data

Yanovsky

Qin

2021

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

View full text Add to dashboard Cite

Multi-image super-resolution using a locally adaptive denoising-based refinement

Cited by 7 publications

References 20 publications

Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data

Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data

Super-Resolution Reconstruction and Its Application Based on Multilevel Main Structure and Detail Boosting

Spatio-Temporal Super-Resolution Reconstruction of Remote Sensing Data

Contact Info

Product

Resources

About