Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSuper-resolution image transfer by a vortex-like metamaterial
314
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
We propose a vortex-like metamaterial device that is capable of transferring image along a spiral route without losing subwavelength information of the image. The super-resolution image can be guided and magnified at the same time with one single design. Our design may provide insights in manipulating super-resolution image in a more flexible manner. Examples are given and illustrated with numerical simulations.
rate research
Read More
Due to the significant information loss in low-resolution (LR) images, it has become extremely challenging to further advance the state-of-the-art of single image super-resolution (SISR). Reference-based super-resolution (RefSR), on the other hand, has proven to be promising in recovering high-resolution (HR) details when a reference (Ref) image with similar content as that of the LR input is given. However, the quality of RefSR can degrade severely when Ref is less similar. This paper aims to unleash the potential of RefSR by leveraging more texture details from Ref images with stronger robustness even when irrelevant Ref images are provided. Inspired by the recent work on image stylization, we formulate the RefSR problem as neural texture transfer. We design an end-to-end deep model which enriches HR details by adaptively transferring the texture from Ref images according to their textural similarity. Instead of matching content in the raw pixel space as done by previous methods, our key contribution is a multi-level matching conducted in the neural space. This matching scheme facilitates multi-scale neural transfer that allows the model to benefit more from those semantically related Ref patches, and gracefully degrade to SISR performance on the least relevant Ref inputs. We build a benchmark dataset for the general research of RefSR, which contains Ref images paired with LR inputs with varying levels of similarity. Both quantitative and qualitative evaluations demonstrate the superiority of our method over state-of-the-art.
We show that a super-resolution process with 100% visibility is characterized by the formation of a point of phase singularity in free space outside the lens in the form of a saddle with topological charge equal to -1. The saddle point is connected to two vortices at the end boundary of the lens, and the two vortices are in turn connected to another saddle point inside the lens. The structure saddle-vortices-saddle is topologically stable. The formation of the saddle point in free space explains also the negative flux of energy present in a certain region of space outside the lens. The circulation strength of the power flow can be controlled by varying the position of the object plane with respect to the lens.
With the recent advancement in deep learning, we have witnessed a great progress in single image super-resolution. However, due to the significant information loss of the image downscaling process, it has become extremely challenging to further advance the state-of-the-art, especially for large upscaling factors. This paper explores a new research direction in super resolution, called reference-conditioned super-resolution, in which a reference image containing desired high-resolution texture details is provided besides the low-resolution image. We focus on transferring the high-resolution texture from reference images to the super-resolution process without the constraint of content similarity between reference and target images, which is a key difference from previous example-based methods. Inspired by recent work on image stylization, we address the problem via neural texture transfer. We design an end-to-end trainable deep model which generates detail enriched results by adaptively fusing the content from the low-resolution image with the texture patterns from the reference image. We create a benchmark dataset for the general research of reference-based super-resolution, which contains reference images paired with low-resolution inputs with varying degrees of similarity. Both objective and subjective evaluations demonstrate the great potential of using reference images as well as the superiority of our results over other state-of-the-art methods.
Image super-resolution is a process to enhance image resolution. It is widely used in medical imaging, satellite imaging, target recognition, etc. In this paper, we conduct continuous modeling and assume that the unknown image intensity function is defined on a continuous domain and belongs to a space with a redundant basis. We propose a new iterative model for single image super-resolution based on an observation: an image is consisted of smooth components and non-smooth components, and we use two classes of approximated Heaviside functions (AHFs) to represent them respectively. Due to sparsity of the non-smooth components, a $L_{1}$ model is employed. In addition, we apply the proposed iterative model to image patches to reduce computation and storage. Comparisons with some existing competitive methods show the effectiveness of the proposed method.
Super-resolution fluorescence microscopy is an important tool in biomedical research for its ability to discern features smaller than the diffraction limit. However, due to its difficult implementation and high cost, the universal application of super-resolution microscopy is not feasible. In this paper, we propose and demonstrate a new kind of super-resolution fluorescence microscopy that can be easily implemented and requires neither additional hardware nor complex post-processing. The microscopy is based on the principle of stepwise optical saturation (SOS), where $M$ steps of raw fluorescence images are linearly combined to generate an image with a $sqrt{M}$-fold increase in resolution compared with conventional diffraction-limited images. For example, linearly combining (scaling and subtracting) two images obtained at regular powers extends resolution by a factor of $1.4$ beyond the diffraction limit. The resolution improvement in SOS microscopy is theoretically infinite but practically is limited by the signal-to-noise ratio. We perform simulations and experimentally demonstrate super-resolution microscopy with both one-photon (confocal) and multiphoton excitation fluorescence. We show that with the multiphoton modality, the SOS microscopy can provide super-resolution imaging deep in scattering samples.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
