Hybrid super-resolution combining example-based single-image and interpolation-based multi-image reconstruction approaches

Bätz, Michel; Eichenseer, Andrea; Seiler, Jurgen; Jonscher, Markus; Kaup, André

doi:10.1109/icip.2015.7350759

Cited by 39 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, SR has been studied with outlier-insensitive observation models including robust error norms [7,8] or, more recently, by space variant Bayesian models [9]. Another trend are hybrid methods that combine single-frame and multi-frame SR to locally enhance the image reconstruction [10].…”

Section: Introductionmentioning

confidence: 99%

Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution

Bercea

Maier

Köhler

2016

2016 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Motion estimation across low-resolution frames and the reconstruction of high-resolution images are two coupled subproblems of multi-frame super-resolution. This paper introduces a new joint optimization approach for motion estimation and image reconstruction to address this interdependence. Our method is formulated via non-linear least squares optimization and combines two principles of robust super-resolution. First, to enhance the robustness of the joint estimation, we propose a confidence-aware energy minimization framework augmented with sparse regularization. Second, we develop a tailor-made Levenberg-Marquardt iteration scheme to jointly estimate motion parameters and the high-resolution image along with the corresponding model confidence parameters. Our experiments on simulated and real images confirm that the proposed approach outperforms decoupled motion estimation and image reconstruction as well as related state-of-the-art joint estimation algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution

Bercea

Maier

Köhler

2016

2016 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…For L1BTV and BEPSR, we used the publicly available MATLAB SR toolbox [23]. For NUISR, we adopted the method in [76]. BVSR is based on source code provided by the authors of [25].…”

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

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

“…The existing image super-resolution reconstruction (SR) can be broadly divided into three categories: interpolationbased methods [1], reconstruction-based methods [2], and learning-based methods [3], [4]. The method based on interpolation mainly includes nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, etc.…”

Section: Introductionmentioning

confidence: 99%

Face Super-Resolution Reconstruction Based on Self-Attention Residual Network

et al. 2020

View full text Add to dashboard Cite

Aiming at the problems of the face image super-resolution reconstruction method based on convolutional neural network, such as single feature extraction scale, low utilization rate of features and blurred face images texture, a model combining convolutional neural network with self-attention mechanism is proposed. Firstly, the shallow features of the image are extracted by the cascaded 3 × 3 convolutional kernels, and then self-attention mechanism is combined with the residual blocks in depth residual network to extract the deep detail features of faces. Finally, the extracted features are fused globally by skip connections, which provide more high-frequency details for face reconstruction. Experiments on Helen, CelebA face datasets and real-world images showed that the proposed method could make full use of facial feature information, and its peak signal to noise ratio (PSNR) and structural similarity (SSIM) were both higher than the comparison methods with better subjective visual effects.

show abstract

Hybrid super-resolution combining example-based single-image and interpolation-based multi-image reconstruction approaches

Cited by 39 publications

References 12 publications

Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution

Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution

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

Face Super-Resolution Reconstruction Based on Self-Attention Residual Network

Contact Info

Product

Resources

About