CN112967378A - Rapid random reconstruction method for large-size pore crack structure in porous medium - Google Patents
Rapid random reconstruction method for large-size pore crack structure in porous medium Download PDFInfo
- Publication number
- CN112967378A CN112967378A CN202110234131.6A CN202110234131A CN112967378A CN 112967378 A CN112967378 A CN 112967378A CN 202110234131 A CN202110234131 A CN 202110234131A CN 112967378 A CN112967378 A CN 112967378A
- Authority
- CN
- China
- Prior art keywords
- reconstruction
- pore
- reference image
- porous medium
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000011148 porous material Substances 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001816 cooling Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims abstract description 8
- 238000010276 construction Methods 0.000 claims abstract description 7
- 239000000463 material Substances 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims abstract description 7
- 238000009826 distribution Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000007670 refining Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 238000005336 cracking Methods 0.000 claims 3
- 238000002922 simulated annealing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000002591 computed tomography Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 238000010894 electron beam technology Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010884 ion-beam technique Methods 0.000 description 1
- 238000000386 microscopy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4023—Scaling of whole images or parts thereof, e.g. expanding or contracting based on decimating pixels or lines of pixels; based on inserting pixels or lines of pixels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a rapid random reconstruction method of a large-size pore crack structure in a porous medium, which belongs to the field of porous medium pore crack structure construction, wherein a pore crack structure image of a porous medium material is obtained as a reference image, coarsening, zooming and sampling are carried out on the full-size statistical function distribution of the reference image, weighting of difference values of different types of statistical function values between the reconstructed image and the reference image is squared, system energy is calculated, a pore crack pixel and a matrix pixel are randomly selected in a reconstruction system to carry out position exchange to construct a new system, the energy of the new system is calculated again, and the probability of receiving the update is calculated according to the difference value of the system energy before and after the update; and continuously repeating the pixel exchange process until the reconstruction system reaches a stable equilibrium state, then cooling according to a certain cooling rule, and repeating the process again to finish reconstruction.
Description
Technical Field
The invention belongs to the field of porous medium pore crack structure construction, and particularly relates to a rapid random reconstruction method of a large-size pore crack structure in a porous medium.
Background
At present, the internal three-dimensional pore fracture structure of the porous medium material is mainly obtained by physical direct scanning imaging technology, such as Computed Tomography (CT), focused ion beam/electron beam dual-beam microscopy imaging technology (FIB/SEM), for example. However, in the practical application process, the physical scanning imaging technology has many disadvantages of long imaging scanning time, high economic cost, and no compromise between field of view (FOV) and resolution, and these disadvantages result in that it cannot be applied and popularized in a wide range.
The numerical random reconstruction method (particularly the simulated annealing algorithm) is a powerful supplement of physical scanning reconstruction, and the method comprises the steps of extracting the characteristics of a reference pore structure by using a plurality of statistical functions, using the characteristics as a target constraint function, guiding a system to be reconstructed to perform iterative evolution gradually towards the direction of the characteristics of the reference pore structure, and further completing numerical random reconstruction of a three-dimensional pore structure in the porous dielectric material. However, the conventional simulated annealing algorithm is complex in construction and calculation procedures of statistical functions, and the updating evolution of a reconstruction system requires great calculation power cost, which seriously hinders the smooth construction of the porous medium large-size pore fracture structure.
BRIEF SUMMARY OF THE PRESENT DISCLOSURE
Aiming at the defects of the prior art, the invention aims to provide a rapid random reconstruction method for a large-size pore crack structure in a porous medium, and solves the problems that the large-size pore crack structure of the porous medium is difficult to construct and the reconstruction system needs great computational power for updating and evolving in the prior art.
The purpose of the invention can be realized by the following technical scheme:
the specific implementation steps are as follows:
a method for rapidly and randomly reconstructing a large-size pore crack structure in a porous medium comprises the following steps:
the method comprises the following steps: acquiring a pore crack structure image of the porous medium material as a reference image, segmenting the pore crack structure in the reference image to generate a binary reference image only containing pore cracks and a matrix, and comprehensively extracting and computing the information of the pore crack structure in the reference image;
step two: coarsening, scaling and sampling the distribution of the full-size statistical function of the reference image, taking the result after the coarsening, scaling and sampling as an initial reference statistical function, taking the hole crack ratio in the reference image as a constraint limiting condition, and generating an initial three-dimensional reconstruction image consistent with the hole crack ratio of the reference image by adopting a random algorithm;
step three: taking the weighted sum of the squares of the difference values of different types of statistical function values between a reconstructed image and a reference image to calculate the energy of an initial system, then randomly selecting a hole crack pixel and a matrix pixel in the reconstructed system to exchange positions to construct a new system, updating the corresponding statistical function values according to an incremental calculation mode, calculating the energy of the new system again, and determining whether to accept the updating according to the difference value of the system energy before and after the updating and a Metropolis criterion;
step four: continuously repeating the three-pixel exchange process until the reconstruction system reaches a stable equilibrium state, then cooling according to a certain cooling rule, repeating the process again, and finishing the reconstruction at the stage when the energy value of the system is lower than a certain specific value through a large amount of cyclic iterative evolution;
step five: and refining the reconstruction finishing system to serve as a new initial reconstruction system, and continuously and circularly repeating the step two, the step three and the step four until the construction of the internal pore crack structure of the porous medium is completed.
Further, the reconstruction method replaces each pixel point with a group of pixel point units.
Further, a method for rapidly and randomly reconstructing a large-size pore crack structure in a porous medium, the system constructed by the method is transmitted to the next stage for reconstruction as an initial system, and the steps recited in claim 2 are continuously repeated for the initial system.
Further, a rapid random reconstruction system of a large-size pore crack structure in the porous medium comprises the reconstruction method.
Furthermore, the device for rapidly and randomly reconstructing the large-size pore structure in the porous medium comprises the system for rapidly and randomly reconstructing the large-size pore structure in the porous medium.
Further, a storage device, which is a system for fast random reconstruction of a large-size pore crack structure in the porous medium.
Further, the energy value of the system in the fourth step is lower than 10-6At this stage, the reconstruction is finished.
Further, the cooling rule of the fourth step is to cool according to an equal ratio sequence with a common ratio smaller than 1.
The invention has the beneficial effects that:
1. the traditional simulated annealing algorithm and the proposed improved simulated annealing algorithm are reconstructed so as to check the high efficiency and accuracy of the proposed algorithm
2. Different from the numerical random reconstruction process of the traditional simulated annealing algorithm, the method disclosed by the invention adopts a mode of combining the scaling of the statistical function with the incremental calculation and updating thereof to construct the porous medium pore fracture structure, and the two can obviously improve the reconstruction efficiency of the three-dimensional large-size pore fracture structure digital model and greatly shorten the time required by reconstruction on the premise of ensuring higher accuracy of the reconstruction result.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a reference image of an embodiment of the present disclosure;
FIG. 2 is a statistical function distribution plot of an embodiment of the present disclosure;
FIG. 3 is a statistical function 2-fold scaling sampling graph of an embodiment of the present disclosure;
FIG. 4 is a final three-dimensional rendering of a porous medium pore fracture structure according to an embodiment of the disclosure;
FIG. 5 is a graph comparing statistical function values for a reconstruction system and a reference system according to an embodiment of the present disclosure;
FIG. 6 is a system flow diagram of an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1 to 6, a method for fast and randomly reconstructing a large-size pore crack structure inside a porous medium is characterized by comprising the following steps:
the method comprises the following steps: and acquiring and preprocessing a reference image, namely acquiring a pore crack structure image of the porous medium material as the reference image by using an SEM or TEM technology, and performing preprocessing operations such as noise filtering, brightness adjustment, contrast enhancement and the like on the reference image so as to improve the quality of the image.
Step two: and generating a reference image, namely segmenting a pore crack structure in the reference image by utilizing a mature threshold value determination algorithm, and generating a binary reference image only containing pore cracks and matrixes so as to calculate and extract the characteristics of the binary reference image by utilizing a related statistical function.
Step three: and (3) selecting and calculating a statistical function, namely respectively selecting a single-point probability function, a two-point probability function and a linear path function (specifically defined as the following formula) to comprehensively and comprehensively extract and calculate and characterize the information of the internal pore structure of the reference image.
S(r)=<I(x)I(x+r)>
Wherein < > represents averaging of internally calculated values; i (x) is an attribute value of a pixel point at the x position in the image, the pore crack is 1, and the matrix is 0; and r is the statistical distance between two pixel points in the image.
Step four: and carrying out coarsening, scaling and sampling on the full-size statistical function distribution of the reference image according to the final target size and the scaling series of the sample to be reconstructed, and simultaneously determining the size of the initial image to be reconstructed. And then, generating an initial three-dimensional reconstruction image consistent with the hole crack occupation ratio of the reference image by adopting a random algorithm by taking the hole crack occupation ratio in the reference image as a constraint limiting condition.
Step five: and calculating and updating system energy, namely calculating the system energy according to the following formula, namely taking the weighted sum of the squares of the difference values of different types of statistical function values between the reconstructed image and the reference image.
Subsequently, a slight perturbation is performed on the reconstruction system, that is, a hole fracture pixel and a matrix pixel are randomly selected inside the reconstruction system for position exchange, and the corresponding statistical function value is updated in a manner of statistical function increment calculation as follows.
Lnew=Lini+[2(Nnew-r)-2(Nini-r)]
In the formula, Sini、LiniAnd Snew、LnewRespectively updating state values of different types of statistical functions before and after the reconstruction system;andrespectively corresponding to individual contribution values of the crack phase pixel points at the selected positions before and after the updating of the reconstruction system to the two-point probability function of the system; n is a radical ofnewAnd NiniRespectively corresponding to the number of the continuous adjacent pore crack phase pixels at the selected position before and after the updating of the reconstruction system.
After the system is updated, the energy of the new system is calculated again, and the probability of receiving the update is calculated according to the following formula according to the difference value of the system energy before and after the update.
In the formula, T is the current evolution temperature of the set reconstruction system.
Step six: and (4) cooling the temperature, continuously repeating the pixel exchange process until the reconstruction system reaches a stable equilibrium state, then cooling according to a certain cooling rule, and repeating the process again. After a large number of loop iteration evolutions, when the energy value of the system is lower than a certain value, the reconstruction at the stage is finished.
Step seven: and refining the reconstruction system, namely refining each pixel point in the system according to the previously adopted scaling series based on the reconstructed system, and specifically, replacing each pixel point by a group of pixel point units so as to improve the resolution of the reconstruction system.
Step eight: and after the reconstruction process is finished, transferring the refined new system to the next stage for reconstruction as an initial system, reconstructing by using a statistical function incremental calculation updating mode again, continuously repeating the process and finally finishing the construction of the internal pore crack structure of the porous medium.
Further, a rapid random reconstruction system of a large-size pore crack structure in the porous medium comprises the reconstruction method.
Furthermore, the device for rapidly and randomly reconstructing the large-size pore structure in the porous medium comprises the system for rapidly and randomly reconstructing the large-size pore structure in the porous medium.
Further, a storage device comprises the rapid random reconfiguration system of the large-size pore crack structure in the porous medium.
Further, the energy value of the system in the fourth step is lower than 10-6At this stage, the reconstruction is finished.
Further, the cooling rule of the fourth step is to cool according to an equal ratio sequence with a common ratio smaller than 1.
Furthermore, different size models are reconstructed according to the method, and the time consumption of the proposed algorithm is compared with that of the traditional algorithm, so that the following obvious points are shown: for the same size model, the time consumption of the proposed algorithm is far less than that of the reconstruction of the traditional algorithm; the computational efficiency advantage of the proposed algorithm appears to be increasingly apparent as the size of the reconstructed model increases. Comprehensive comparison shows that the numerical reconstruction of the three-dimensional large-size hole fracture structure digital model can be accurately and quickly completed by the proposed algorithm, the statistical function value of the reconstructed model of the proposed algorithm is better in accordance with the reference statistical function value, and the proposed algorithm is higher in accuracy and can be popularized in a large range.
Time consuming comparison of reconstructed model Table 1
Principle of operation
Calculating system energy through the weighted sum of the difference squares of different types of statistical function values between a reconstructed image and a reference image, randomly selecting a hole crack pixel and a matrix pixel in the reconstructed system to perform position exchange to construct a new system, calculating the energy of the new system again, and calculating the probability of receiving the update according to the difference of the system energy before and after the update; and continuously repeating the pixel exchange process until the reconstruction system reaches a stable equilibrium state, then cooling according to a certain cooling rule, and repeating the process again to finish reconstruction.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed.
Claims (8)
1. A rapid random reconstruction method for a large-size pore crack structure in a porous medium is characterized by comprising the following steps:
the method comprises the following steps: acquiring a pore crack structure image of the porous medium material as a reference image, segmenting the pore crack structure in the reference image to generate a binary reference image only containing pore cracks and a matrix, and comprehensively extracting and computing the information of the pore crack structure in the reference image;
step two: coarsening, scaling and sampling the distribution of the full-size statistical function of the reference image, taking the result after the coarsening, scaling and sampling as an initial reference statistical function, taking the hole crack ratio in the reference image as a constraint limiting condition, and generating an initial three-dimensional reconstruction image consistent with the hole crack ratio of the reference image by adopting a random algorithm;
step three: taking the weighted sum of the squares of the difference values of different types of statistical function values between a reconstructed image and a reference image to calculate the energy of an initial system, then randomly selecting a hole crack pixel and a matrix pixel in the reconstructed system to exchange positions to construct a new system, updating the corresponding statistical function values according to an incremental calculation mode, calculating the energy of the new system again, and determining whether to accept the updating according to the difference value of the system energy before and after the updating and a Metropolis criterion;
step four: continuously repeating the three-pixel exchange process until the reconstruction system reaches a stable equilibrium state, then cooling according to a certain cooling rule, repeating the process again, and finishing the reconstruction at the stage when the energy value of the system is lower than a certain specific value through a large amount of cyclic iterative evolution;
step five: and refining the reconstruction finishing system to serve as a new initial reconstruction system, and continuously and circularly repeating the step two, the step three and the step four until the construction of the internal pore crack structure of the porous medium is completed.
2. The method of claim 1, wherein the reconstruction method replaces each pixel with a group of pixel units.
3. The method for fast and randomly reconstructing large-size pore cracking structures in porous media according to claim 2, wherein the system constructed by the method according to claim 2 is transferred to a next stage for reconstruction as an initial system, and the steps according to claim 1 are repeated for the initial system.
4. A system for rapid stochastic reconstruction of large pore fissured structures within porous media comprising the reconstruction method of claim 3.
5. A device for fast random reconstruction of large-size pore cracking structures inside porous media comprises the system for fast random reconstruction of large-size pore cracking structures inside porous media according to claim 4.
6. A storage device, wherein the storage device is the system for fast random reconstruction of large-scale pore crack structures inside porous media according to claim 4.
7. The method for fast and randomly reconstructing large-size pore crack structures in porous media according to claim 1, wherein the energy value of the system in the fourth step is less than 10-6At this stage, the reconstruction is finished.
8. The method for rapidly and randomly reconstructing the large-size pore crack structure in the porous medium according to claim 1, wherein the temperature reduction rule of the fourth step is to reduce the temperature according to an equal ratio sequence with a common ratio less than 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110234131.6A CN112967378A (en) | 2021-03-03 | 2021-03-03 | Rapid random reconstruction method for large-size pore crack structure in porous medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110234131.6A CN112967378A (en) | 2021-03-03 | 2021-03-03 | Rapid random reconstruction method for large-size pore crack structure in porous medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112967378A true CN112967378A (en) | 2021-06-15 |
Family
ID=76276705
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110234131.6A Pending CN112967378A (en) | 2021-03-03 | 2021-03-03 | Rapid random reconstruction method for large-size pore crack structure in porous medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112967378A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112132965A (en) * | 2020-09-25 | 2020-12-25 | 中国矿业大学 | Multi-scale characterization method for rock-soil body pore fracture structure |
CN112233166A (en) * | 2020-09-11 | 2021-01-15 | 安徽理工大学 | Pore size distribution evaluation method based on porous medium three-dimensional pore space image |
CN112381916A (en) * | 2020-12-08 | 2021-02-19 | 西南石油大学 | Digital rock core three-dimensional structure reconstruction method using two-dimensional slice image |
-
2021
- 2021-03-03 CN CN202110234131.6A patent/CN112967378A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112233166A (en) * | 2020-09-11 | 2021-01-15 | 安徽理工大学 | Pore size distribution evaluation method based on porous medium three-dimensional pore space image |
CN112132965A (en) * | 2020-09-25 | 2020-12-25 | 中国矿业大学 | Multi-scale characterization method for rock-soil body pore fracture structure |
CN112381916A (en) * | 2020-12-08 | 2021-02-19 | 西南石油大学 | Digital rock core three-dimensional structure reconstruction method using two-dimensional slice image |
Non-Patent Citations (2)
Title |
---|
MARINA V. KARSANINA,KIRILL M. GERKE: "Hierarchical Optimization: Fast and Robust Multiscale Stochastic Reconstructions with Rescaled Correlation Functions", 《PHYSICAL REVIEW LETTERS》, vol. 121, no. 26, 28 December 2018 (2018-12-28), pages 2 - 3 * |
宋帅兵: "高庙子膨润土孔隙结构多尺度特征及其渗流特性研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》, vol. 2021, no. 01, 15 January 2021 (2021-01-15), pages 3 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111754403B (en) | Image super-resolution reconstruction method based on residual learning | |
Wang et al. | Esrgan: Enhanced super-resolution generative adversarial networks | |
CN111932461B (en) | Self-learning image super-resolution reconstruction method and system based on convolutional neural network | |
CN111583107A (en) | Image super-resolution reconstruction method and system based on attention mechanism | |
Yang et al. | Image super-resolution based on deep neural network of multiple attention mechanism | |
CN112330761B (en) | Deep ECT image enhancement method based on mixed precision training | |
Song et al. | Grouped multi-scale network for real-world image denoising | |
CN109993702A (en) | Based on the language of the Manchus image super-resolution rebuilding method for generating confrontation network | |
CN116682120A (en) | Multilingual mosaic image text recognition method based on deep learning | |
CN107622482B (en) | Image fusion method based on leucorrhea microscopic imaging | |
CN107424119B (en) | Super-resolution method of single image | |
Yang et al. | An image super-resolution network based on multi-scale convolution fusion | |
CN116071352A (en) | Method for generating surface defect image of electric power safety tool | |
CN110288529A (en) | A kind of single image super resolution ratio reconstruction method being locally synthesized network based on recurrence | |
Liu et al. | From coarse to fine: Hierarchical pixel integration for lightweight image super-resolution | |
CN112967378A (en) | Rapid random reconstruction method for large-size pore crack structure in porous medium | |
CN112862946B (en) | Gray rock core image three-dimensional reconstruction method for generating countermeasure network based on cascade condition | |
CN116091319A (en) | Image super-resolution reconstruction method and system based on long-distance context dependence | |
Wang et al. | Deep learning super‐resolution electron microscopy based on deep residual attention network | |
Wu et al. | Pyramidal dense attention networks for lightweight image super-resolution | |
CN112819955A (en) | Improved reconstruction method based on digital image three-dimensional model | |
Niu et al. | Lightweight and accurate single image super-resolution with channel segregation network | |
Zhou et al. | Efficient network removing feature redundancy for single image super-resolution | |
He et al. | Pyramid Fusion Attention Network For Single Image Super-Resolution | |
CN117236201B (en) | Diffusion and ViT-based downscaling method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210615 |
|
RJ01 | Rejection of invention patent application after publication |