A qualitative study of Exemplar based Image Inpainting

Shroff, Megha; Bombaywala, Md. Salman R.

doi:10.1007/s42452-019-1775-7

Cited by 11 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shim correction was performed using Matlab 13 exemplar‐based algorithm. The algorithm search for optimal pattern patches within the projection based on pixel values and replaces the target patch pixels 14 . The patch size was heuristically determined equal to 8 × 8 pixels and the patch fill priority was tensor based.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MV‐based relative electron density estimation (iMREDe) for MR‐LINAC dose calculation

Myronakis,

Hu,

Jacobson

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundMR‐LINAC systems have been increasingly utilized for real‐time imaging in adaptive treatments worldwide. Challenges in MR representation of air cavities and subsequent estimation of electron density maps impede planning efficiency and may lead to dose calculation uncertainties.PurposeTo demonstrate the generation of accurate electron density maps using the primary MV beam with a flat‐panel imager.MethodsThe ViewRay MRIdian MR‐LINAC system was modeled digitally for Monte Carlo simulations. Iron shimming, the magnetic field, and the proposed flat panel detector were included in the model. The effect of the magnetic field on the detector response was investigated. Acquisition of projections over 360 degrees was simulated for digital phantoms of the Catphan 505 phantom and a patient treated for Head and Neck cancer. Shim patterns on the projections were removed and detector noise linearity was assessed. Electron density maps were generated for the digital patient phantom using the flat‐panel detector and compared with actual treatment planning CT generated electron density maps of the same patient.ResultsThe effect of the magnetic field on the detector point‐spread function (PSF) was found to be substantial for field strengths above 50 mT. Shims correction in the projection images using air normalization and in‐painting effectively removed reconstruction artifacts without affecting noise linearity. The relative difference between reconstructed electron density maps from the proposed method and electron density maps generated from the treatment planning CT was 11% on average along all slices included in the iMREDe reconstruction.ConclusionsThe proposed iMREDe technique demonstrated the feasibility of generating accurate electron densities for the ViewRay MRIdian MR‐LINAC system with a flat‐panel imager and the primary MV beam. This work is a step towards reducing the time and effort required for adaptive radiotherapy in the current ViewRay MR‐LINAC systems.

show abstract

Section: Methodsmentioning

confidence: 99%

“…These patches are treated as damaged parts of the projection image and corrected by the inpainting algorithm. The shim correction was performed using Matlab 13 exemplar-based algorithm. The algorithm search for optimal pattern patches within the projection based on pixel values and replaces the target patch pixels.…”

Section: Simulated Cbct Acquisitionmentioning

confidence: 99%

MV‐based relative electron density estimation (iMREDe) for MR‐LINAC dose calculation

Myronakis,

Hu,

Jacobson

et al. 2024

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Traditional methods include interpolation and PDE or convolution based methods like Bertalmio's, Telea's and Oliveira's algorithms (Bertalmio et al, 2001;Telea, 2004;Richard & Chang, 2001), but these methods only inpaint by looking at neighbouring pixels within each image. Exemplar-based inpainting matches patches in a specific order (Shroff & Bombaywala, 2019), but these methods use defined low-level patterns that do not capture semantic structure in the images. The Navier-Stokes (Bertalmio et al, 2001) inpainting algorithm uses ideas from classical fluid dynamics and is used as a baseline for our problem.…”

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Processes for Inpainting Satellite Images

Pondaven¹,

Bakler²,

Guo³

et al. 2022

Preprint

View full text Add to dashboard Cite

The widespread availability of satellite images has allowed researchers to model complex systems such as disease dynamics. However, many satellite images have missing values due to measurement defects, which render them unusable without data imputation. For example, the scanline corrector for the LANDSAT 7 satellite broke down in 2003, resulting in a loss of around 20% of its data.Inpainting involves predicting what is missing based on the known pixels and is an old problem in image processing, classically based on PDEs or interpolation methods, but recent deep learning approaches have shown promise. However, many of these methods do not explicitly take into account the inherent spatiotemporal structure of satellite images. In this work, we cast satellite image inpainting as a natural meta-learning problem, and propose using convolutional neural processes (ConvNPs) where we frame each satellite image as its own task or 2D regression problem. We show ConvNPs can outperform classical methods and state-of-the-art deep learning inpainting models on a scanline inpainting problem for LANDSAT 7 satellite images, assessed on a variety of in and out-of-distribution images. * Equal contribution. † Order decided via a coin toss.

show abstract

“…This algorithm concentrates on rectangular-shaped holes, which are frequently considered to be in the middle of image and the search is incredibly poor and I prone to inaccurate results [5]. This is a main drawback of Exemplar based method and eventually decrease the usefulness of these models in the application [6]. A new inpainting algorithm called Fast Marching Method [7] the basis for obtaining FMM is the propagation of an image smoothness estimator down the image gradient.…”

Section: Introductionmentioning

confidence: 99%

Reconv: Repeated Convolutional Strategies for Advanced Image Inpainting

Jini.P,

K.K

2024

Preprint

View full text Add to dashboard Cite

Image inpainting is a promising but challenging approach that fills in huge free-form empty areas in images. Most of the recent papers concentrate on splitting masked image into two matrices of valid and invalid elements which makes the system more complex. This paper proposes a novel algorithm named ReConv which uses a repeated standard convolution operation which treats valid and invalid elements of an image in the same manner. The outcomes of our suggested method, ReConv, shows that, in comparison to earlier approaches, our system produces outputs that are more adaptable with good quality for real world applications. Our suggested technique enables users quickly modify faces, eliminate distracting items, change image layouts, and remove unwanted text. An extensive comparison study on two types of datasets validates our method. The effectiveness of the suggested strategy was evaluated using different measures such as PSNR, SSIM and FID. The results show that our recommended approach excels in performance compared to the existing modern methods.

show abstract

A qualitative study of Exemplar based Image Inpainting

Cited by 11 publications

References 23 publications

MV‐based relative electron density estimation (iMREDe) for MR‐LINAC dose calculation

MV‐based relative electron density estimation (iMREDe) for MR‐LINAC dose calculation

Convolutional Neural Processes for Inpainting Satellite Images

Reconv: Repeated Convolutional Strategies for Advanced Image Inpainting

Contact Info

Product

Resources

About