The Five Plague Gods(五瘟神) in the Shuilu(水陆) murals from the Ming and Qing dynasties exemplify a distinctive manifestation of plague gods image developed under the pedigree of Taoist gods.As a significant system f...The Five Plague Gods(五瘟神) in the Shuilu(水陆) murals from the Ming and Qing dynasties exemplify a distinctive manifestation of plague gods image developed under the pedigree of Taoist gods.As a significant system for expelling disasters in Shuilu,the depiction of the Five Plague Gods prominently merges human beings and livestock.This shape form to a large extent,draws on the image of Nuo(傩),a figure reflecting an imagination of the host of plague pathogens.In terms of the numbers of gods,it aligns with the conceptual framework of Wu Xing(五行 the five elements),a foundational principle in traditional Chinese medicine.The internal cultural connection highlights the means of plague prevention and control in China,as well as the external reflection of plague culture.Through multi-dimensional interpretations with the double proof method,this article dissects the formation,core elements,and cultural characteristics of the beliefs in the Five Plague Gods reflected in the Shuilu murals,and transcends mere visual semantics,offering a deeper understanding of these complex cultural symbols.展开更多
This study aims to further promote the inheritance and innovative development of intangible cultural heritage in Yunnan Province,promote the protection,inheritance,integration,and innovation of ethnic culture in Lijia...This study aims to further promote the inheritance and innovative development of intangible cultural heritage in Yunnan Province,promote the protection,inheritance,integration,and innovation of ethnic culture in Lijiang,strengthen the protection and inheritance of Baisha murals in Lijiang,and change the teaching of art design majors in vocational colleges in Yunnan.Given the lack of traditional Chinese culture and local ethnic culture,this article focuses on the teaching of art design majors in Yunnan vocational colleges.It explores the construction model of the cultural inheritance and innovation carrier of Lijiang Baisha murals to meet the spiritual and cultural needs of the local people,and efforts will be made to promote the high-quality development of the Baisha ethnic area in Lijiang.展开更多
Ceramic relief mural is a contemporary landscape art that is carefully designed based on human nature,culture,and architectural wall space,combined with social customs,visual sensibility,and art.It may also become the...Ceramic relief mural is a contemporary landscape art that is carefully designed based on human nature,culture,and architectural wall space,combined with social customs,visual sensibility,and art.It may also become the main axis of ceramic art in the future.Taiwan public ceramic relief murals(PCRM)are most distinctive with the PCRM pioneered by Pan-Hsiung Chu of Meinong Kiln in 1987.In addition to breaking through the limitations of traditional public ceramic murals,Chu leveraged local culture and sensibility.The theme of art gives PCRM its unique style and innovative value throughout the Taiwan region.This study mainly analyzes and understands the design image of public ceramic murals,taking Taiwan PCRM’s design and creation as the scope,and applies STEEP analysis,that is,the social,technological,economic,ecological,and political-legal environments are analyzed as core factors;eight main important factors in the artistic design image of ceramic murals are evaluated.Then,interpretive structural modeling(ISM)is used to establish five levels,analyze the four main problems in the main core factor area and the four main target results in the affected factor area;and analyze the problem points and target points as well as their causal relationships.It is expected to sort out the relationship between these factors,obtain the hierarchical relationship of each factor,and provide a reference basis and research methods.展开更多
Due to the limitations of a priori knowledge and convolution operation,the existing image restoration techniques cannot be directly applied to the cultural relics mural restoration,in order to more accurately restore ...Due to the limitations of a priori knowledge and convolution operation,the existing image restoration techniques cannot be directly applied to the cultural relics mural restoration,in order to more accurately restore the original appearance of the cultural relics mural images,an image restoration based on the denoising diffusion probability model(Denoising Diffusion Probability Model(DDPM))and the Transformer method.The process involves two steps:in the first step,the damaged mural image is firstly utilized as the condition to generate the noise image,using the time,condition and noise image patch as the inputs to the noise prediction network,capturing the global dependencies in the input sequence through the multi-attentionmechanismof the input sequence and feedforward neural network processing,and designing a long skip connection between the shallow and deep layers in the Transformer blocks between the shallow and deep layers using long skip connections to fuse the feature information of global and local outputs to maintain the overall consistency of the restoration results;In the second step,taking the noisy image as a condition to direct the diffusion model to back sample to generate the restored image.Experiment results show that the PSNR and SSIM of the proposedmethod are improved by 2%to 9%and 1%to 3.3%,respectively,which are compared to the comparison methods.This study proposed synthesizes the advantages of the diffusionmodel and deep learningmodel to make themural restoration results more accurate.展开更多
Dunhuang murals are gems of Chinese traditional art. This paper demonstrates a simple, yet powerful method to automatically identify the aesthetic visual style that lies in Dunhuang murals. Based on the art knowledge ...Dunhuang murals are gems of Chinese traditional art. This paper demonstrates a simple, yet powerful method to automatically identify the aesthetic visual style that lies in Dunhuang murals. Based on the art knowledge on Dunhuang murals, the method explicitly predicts some of possible image attributes that a human might use to understand the aesthetic visual style of a mural. These cues fall into three broad types: ① composition attributes related to mural layout or configuration; ② color attributes related to color types depicted; ③ brightness attributes related to bright conditions. We show that a classifier trained on these attributes can provide an efficient way to predict the aesthetic visual style of Dunhuang murals.展开更多
The F8hai(Sea of Dharma)T6mple is locatedat the southern foot of the beautiful CuiweiMountain in the Shongshan District ofthewesternsuburb of Begng．With a history of over 500 years,the temp巨e was completed in 1143 a...The F8hai(Sea of Dharma)T6mple is locatedat the southern foot of the beautiful CuiweiMountain in the Shongshan District ofthewesternsuburb of Begng．With a history of over 500 years,the temp巨e was completed in 1143 and named展开更多
Traditional murals and their image remains are an important art category and visual language,as well as a special architectural type.Traditional murals are roughly divided into temples,grottoes,tombs and other types a...Traditional murals and their image remains are an important art category and visual language,as well as a special architectural type.Traditional murals are roughly divided into temples,grottoes,tombs and other types according to space,function and function.No matter what type of traditional mural,its basic function is to convey information through visual images.With the development and application of information technology and digital technology,traditional mural paintings have undergone changes in space,material,and form in the exhibition-gradually transitioning from ancient rock murals to multi-sensory participation under digital screen display.Because of the intervention of digital media,in many digital mural exhibitions in recent years,not only the spatial presentation and viewing of murals have formed a multi-dimensional visual correspondence but also the exhibition language of murals is enriched or supplemented.展开更多
Dunhuang painters are a subgroup within the category of artisans.Although they represent only one type of artisan,their significance in Dunhuang is undeniable.The work of these painters goes beyond mere artistry;the h...Dunhuang painters are a subgroup within the category of artisans.Although they represent only one type of artisan,their significance in Dunhuang is undeniable.The work of these painters goes beyond mere artistry;the historical materials they have left behind are of great importance.Through their images,they tell the story of the development of ancient civilization.Every mural and every sculpture not only represents the manifestation of Dunhuang civilization but also serves as a vital addition to the larger narrative of Chinese history.Dunhuang painters are both ancient and contemporary figures.The ancient Dunhuang painters left us with inexhaustible spiritual and material wealth.Contemporary Dunhuang painters continue to provide us with a spirit of innovation and an unbroken legacy that evolves with the times.展开更多
Paintings in Ethiopia have a long history.Ancient peoples of Ethiopia and others who had lived in caves developed a tradition of depicting animal motifs they domesticated and their daily activities.The growth of sacre...Paintings in Ethiopia have a long history.Ancient peoples of Ethiopia and others who had lived in caves developed a tradition of depicting animal motifs they domesticated and their daily activities.The growth of sacred painting in Ethiopia was a result of the introduction of Christianity in the 4th century AD.In addition the Ethiopian Orthodox Church approval of using paintings as a medium of teaching contributed for this development.Due to lack of evidences and insufficient researches conducted in the field little is known about ancient history of Ethiopian paintings.Most of the researches conducted focused on medieval period religious paintings and lately developed.The aim of this study is to investigate the development,significance,and challenges of churches with murals of the Gondarian painting style.The study was qualitative in approach and descriptive in design.In order to get valuable information for the study both primary and secondary sources were collected through interview,observation,and review of related literatures.And the data obtained through the above mentioned data gathering tools were analyzed qualitatively.The finding revealed that medieval period in Ethiopia witnessed the development of religious paintings mainly during the Gondarian period.Religious paintings of the period painted mainly on foundations of parchments,wall,and wood panel.Like other tourist attractions,wall paintings contributed a lot in attracting both domestic and international tourists.Due to several man-made and natural problems those wall paintings faced serious challenges which need an immediate intervention from the concerned bodies.展开更多
The Mexican mural movement,also known as Mexican muralism,is recognized as one of the most significant art movements of the 20th century.It developed in the aftermath of the Mexican Revolution,which took place between...The Mexican mural movement,also known as Mexican muralism,is recognized as one of the most significant art movements of the 20th century.It developed in the aftermath of the Mexican Revolution,which took place between 1910 and 1920.The country was striving to rebuild and unify after years of conflict,and muralism became a powerful tool for this transformation.展开更多
In the thousand-year-old mural of Mogao Grottoes in Dunhuang,a special symbol tells the story of exchanges among civilisations.Three Rabbits Sharing Three Ears depicts three rabbits chasing each other,with each two sh...In the thousand-year-old mural of Mogao Grottoes in Dunhuang,a special symbol tells the story of exchanges among civilisations.Three Rabbits Sharing Three Ears depicts three rabbits chasing each other,with each two sharing one ear.It is said that its earliest version appeared in Dunhuang in the 6th century,and it had travelled across the desert along the ancient Silk Road,over mountains and rivers,leaping onto British ceramic tiles,integrating into Egyptian pottery and jumping cross the clock faces of German churches.展开更多
For the existing deep learning image restoration methods,the joint guidance of structure and texture information is not considered,which leads to structural disorder and texture blur in the restoration results.A gener...For the existing deep learning image restoration methods,the joint guidance of structure and texture information is not considered,which leads to structural disorder and texture blur in the restoration results.A generative adversarial mural inpainting algorithm based on structural and texture hybrid enhancement was proposed.Firstly,the structure guidance branch composed of dynamic convolution cascade was constructed to improve the expression ability of structure features,and the structure information was used to guide the encoder coding to enhance the edge contour information of the coding feature map.Then,the multi-granularity feature extraction module was designed to obtain the texture features of texture guided branches,and the multi-scale texture information was used to guide the decoder to reconstruct and repair,so as to improve the texture consistency of murals.Finally,skip connection was used to promote the feature sharing of structure and texture features,and the spectral-normalized PatchGAN discriminator was used to complete the mural restoration.The digital restoration experiment results of real Dunhuang murals showed that the proposed method was better than the comparison algorithms in both subjective and objective evaluation,and the restoration results were clearer and more natural.展开更多
Sparse representation has been highly successful in various tasks related to image processing and computer vision.For ancient mural image inpainting,traditional group sparse representation models usually lead to struc...Sparse representation has been highly successful in various tasks related to image processing and computer vision.For ancient mural image inpainting,traditional group sparse representation models usually lead to structure blur and line discontinuity due to the construction of similarity group solely based on the Euclidean distance and the randomness of dictionary initialization.To address the aforementioned issues,an improved curvature Gabor transform and group sparse representation(CGabor-GSR)model for ancient Dunhuang mural inpainting is proposed.To begin with,mutual information is introduced to weight the Euclidean distance,and then the weighted Euclidean distance acts as a new standard of similarity group.Subsequently,to mitigate the randomness of dictionary initialization,a curvature Gabor wavelet transform is proposed to extract the features and initialize the feature dictionary with dimension reduction based on principal component analysis(PCA).Ultimately,singular value decomposition(SVD)and split Bregman iteration(SBI)can be used to resolve the CGabor-GSR model to reconstruct the mural images.Experimental results on Dunhuang mural inpainting demonstrate tha the proposed CGabor-GSR achieves a better performance than compared algorithms in both objective and visual evaluation.展开更多
In the long history of more than 1 500 years,Dunhuang murals suffered from various deteriorations causing irreversible damage such as falling off,fading,and so on.However,the existing Dunhuang mural restoration method...In the long history of more than 1 500 years,Dunhuang murals suffered from various deteriorations causing irreversible damage such as falling off,fading,and so on.However,the existing Dunhuang mural restoration methods are time-consuming and not feasible to facilitate cultural dissemination and permanent inheritance.Inspired by cultural computing using artificial intelligence,gated-convolution-based dehaze net(GD-Net) was proposed for Dunhuang mural refurbishment and comprehensive protection.First,a neural network with gated convolution was applied to restore the falling off areas of the mural to ensure the integrity of the mural content.Second,a dehaze network was applied to enhance image quality to cope with the fading of the mural.Besides,a Dunhuang mural dataset was presented to meet the needs of deep learning approach,containing 1 180 images from the Cave 290 and Cave 112 of the Mogao Grottoes.The experimental results demonstrate the effectiveness and superiority of GD-Net.展开更多
Mural paintings hold significant historical information and possess substantial artistic and cultural value.However,murals are inevitably damaged by natural environmental factors such as wind and sunlight,as well as b...Mural paintings hold significant historical information and possess substantial artistic and cultural value.However,murals are inevitably damaged by natural environmental factors such as wind and sunlight,as well as by human activities.For this reason,the study of damaged areas is crucial for mural restoration.These damaged regions differ significantly from undamaged areas and can be considered abnormal targets.Traditional manual visual processing lacks strong characterization capabilities and is prone to omissions and false detections.Hyperspectral imaging can reflect the material properties more effectively than visual characterization methods.Thus,this study employs hyperspectral imaging to obtain mural information and proposes a mural anomaly detection algorithm based on a hyperspectral multi-scale residual attention network(HM-MRANet).The innovations of this paper include:(1)Constructing mural painting hyperspectral datasets.(2)Proposing a multi-scale residual spectral-spatial feature extraction module based on a 3D CNN(Convolutional Neural Networks)network to better capture multiscale information and improve performance on small-sample hyperspectral datasets.(3)Proposing the Enhanced Residual Attention Module(ERAM)to address the feature redundancy problem,enhance the network’s feature discrimination ability,and further improve abnormal area detection accuracy.The experimental results show that the AUC(Area Under Curve),Specificity,and Accuracy of this paper’s algorithm reach 85.42%,88.84%,and 87.65%,respectively,on this dataset.These results represent improvements of 3.07%,1.11%and 2.68%compared to the SSRN algorithm,demonstrating the effectiveness of this method for mural anomaly detection.展开更多
In order to solve the problem of the lack of ornamental value and research value of ancient mural paintings due to low resolution and fuzzy texture details,a super resolution(SR)method based on generative adduction ne...In order to solve the problem of the lack of ornamental value and research value of ancient mural paintings due to low resolution and fuzzy texture details,a super resolution(SR)method based on generative adduction network(GAN)was proposed.This method reconstructed the detail texture of mural image better.Firstly,in view of the insufficient utilization of shallow image features,information distillation blocks(IDB)were introduced to extract shallow image features and enhance the output results of the network behind.Secondly,residual dense blocks with residual scaling and feature fusion(RRDB-Fs)were used to extract deep image features,which removed the BN layer in the residual block that affected the quality of image generation,and improved the training speed of the network.Furthermore,local feature fusion and global feature fusion were applied in the generation network,and the features of different levels were merged together adaptively,so that the reconstructed image contained rich details.Finally,in calculating the perceptual loss,the brightness consistency between the reconstructed fresco and the original fresco was enhanced by using the features before activation,while avoiding artificial interference.The experimental results showed that the peak signal-to-noise ratio and structural similarity metrics were improved compared with other algorithms,with an improvement of 0.512 dB-3.016 dB in peak signal-to-noise ratio and 0.009-0.089 in structural similarity,and the proposed method had better visual effects.展开更多
基金financed by the grants from Shanxi Province Postgraduate Education Innovation Plan (No. 2023KY126)Humanities and Social Sciences Research Project of The Ministry of Ecuation (No. 23YJAZH182)。
文摘The Five Plague Gods(五瘟神) in the Shuilu(水陆) murals from the Ming and Qing dynasties exemplify a distinctive manifestation of plague gods image developed under the pedigree of Taoist gods.As a significant system for expelling disasters in Shuilu,the depiction of the Five Plague Gods prominently merges human beings and livestock.This shape form to a large extent,draws on the image of Nuo(傩),a figure reflecting an imagination of the host of plague pathogens.In terms of the numbers of gods,it aligns with the conceptual framework of Wu Xing(五行 the five elements),a foundational principle in traditional Chinese medicine.The internal cultural connection highlights the means of plague prevention and control in China,as well as the external reflection of plague culture.Through multi-dimensional interpretations with the double proof method,this article dissects the formation,core elements,and cultural characteristics of the beliefs in the Five Plague Gods reflected in the Shuilu murals,and transcends mere visual semantics,offering a deeper understanding of these complex cultural symbols.
文摘This study aims to further promote the inheritance and innovative development of intangible cultural heritage in Yunnan Province,promote the protection,inheritance,integration,and innovation of ethnic culture in Lijiang,strengthen the protection and inheritance of Baisha murals in Lijiang,and change the teaching of art design majors in vocational colleges in Yunnan.Given the lack of traditional Chinese culture and local ethnic culture,this article focuses on the teaching of art design majors in Yunnan vocational colleges.It explores the construction model of the cultural inheritance and innovation carrier of Lijiang Baisha murals to meet the spiritual and cultural needs of the local people,and efforts will be made to promote the high-quality development of the Baisha ethnic area in Lijiang.
文摘Ceramic relief mural is a contemporary landscape art that is carefully designed based on human nature,culture,and architectural wall space,combined with social customs,visual sensibility,and art.It may also become the main axis of ceramic art in the future.Taiwan public ceramic relief murals(PCRM)are most distinctive with the PCRM pioneered by Pan-Hsiung Chu of Meinong Kiln in 1987.In addition to breaking through the limitations of traditional public ceramic murals,Chu leveraged local culture and sensibility.The theme of art gives PCRM its unique style and innovative value throughout the Taiwan region.This study mainly analyzes and understands the design image of public ceramic murals,taking Taiwan PCRM’s design and creation as the scope,and applies STEEP analysis,that is,the social,technological,economic,ecological,and political-legal environments are analyzed as core factors;eight main important factors in the artistic design image of ceramic murals are evaluated.Then,interpretive structural modeling(ISM)is used to establish five levels,analyze the four main problems in the main core factor area and the four main target results in the affected factor area;and analyze the problem points and target points as well as their causal relationships.It is expected to sort out the relationship between these factors,obtain the hierarchical relationship of each factor,and provide a reference basis and research methods.
基金financial support from Hunan Provincial Natural Science and Technology Fund Project(Grant No.2022JJ50077)Natural Science Foundation of Hunan Province(Grant No.2024JJ8055).
文摘Due to the limitations of a priori knowledge and convolution operation,the existing image restoration techniques cannot be directly applied to the cultural relics mural restoration,in order to more accurately restore the original appearance of the cultural relics mural images,an image restoration based on the denoising diffusion probability model(Denoising Diffusion Probability Model(DDPM))and the Transformer method.The process involves two steps:in the first step,the damaged mural image is firstly utilized as the condition to generate the noise image,using the time,condition and noise image patch as the inputs to the noise prediction network,capturing the global dependencies in the input sequence through the multi-attentionmechanismof the input sequence and feedforward neural network processing,and designing a long skip connection between the shallow and deep layers in the Transformer blocks between the shallow and deep layers using long skip connections to fuse the feature information of global and local outputs to maintain the overall consistency of the restoration results;In the second step,taking the noisy image as a condition to direct the diffusion model to back sample to generate the restored image.Experiment results show that the PSNR and SSIM of the proposedmethod are improved by 2%to 9%and 1%to 3.3%,respectively,which are compared to the comparison methods.This study proposed synthesizes the advantages of the diffusionmodel and deep learningmodel to make themural restoration results more accurate.
基金the National Basic Research Program(973)of China(No.2012CB725305)the National Key Technology R&D Program of China(No.2012BAH03F02)
文摘Dunhuang murals are gems of Chinese traditional art. This paper demonstrates a simple, yet powerful method to automatically identify the aesthetic visual style that lies in Dunhuang murals. Based on the art knowledge on Dunhuang murals, the method explicitly predicts some of possible image attributes that a human might use to understand the aesthetic visual style of a mural. These cues fall into three broad types: ① composition attributes related to mural layout or configuration; ② color attributes related to color types depicted; ③ brightness attributes related to bright conditions. We show that a classifier trained on these attributes can provide an efficient way to predict the aesthetic visual style of Dunhuang murals.
文摘The F8hai(Sea of Dharma)T6mple is locatedat the southern foot of the beautiful CuiweiMountain in the Shongshan District ofthewesternsuburb of Begng．With a history of over 500 years,the temp巨e was completed in 1143 and named
基金This study was supported by the“2019 Planning Fund Project for Humanities and Social Science Research,Ministry of Education,China”Project title:“Research on the Image of Utensils in the Remains of Ancient Murals in Shanxi-From Song and Jin to Ming and Qing”(approval number:19YJA760066).
文摘Traditional murals and their image remains are an important art category and visual language,as well as a special architectural type.Traditional murals are roughly divided into temples,grottoes,tombs and other types according to space,function and function.No matter what type of traditional mural,its basic function is to convey information through visual images.With the development and application of information technology and digital technology,traditional mural paintings have undergone changes in space,material,and form in the exhibition-gradually transitioning from ancient rock murals to multi-sensory participation under digital screen display.Because of the intervention of digital media,in many digital mural exhibitions in recent years,not only the spatial presentation and viewing of murals have formed a multi-dimensional visual correspondence but also the exhibition language of murals is enriched or supplemented.
文摘Dunhuang painters are a subgroup within the category of artisans.Although they represent only one type of artisan,their significance in Dunhuang is undeniable.The work of these painters goes beyond mere artistry;the historical materials they have left behind are of great importance.Through their images,they tell the story of the development of ancient civilization.Every mural and every sculpture not only represents the manifestation of Dunhuang civilization but also serves as a vital addition to the larger narrative of Chinese history.Dunhuang painters are both ancient and contemporary figures.The ancient Dunhuang painters left us with inexhaustible spiritual and material wealth.Contemporary Dunhuang painters continue to provide us with a spirit of innovation and an unbroken legacy that evolves with the times.
文摘Paintings in Ethiopia have a long history.Ancient peoples of Ethiopia and others who had lived in caves developed a tradition of depicting animal motifs they domesticated and their daily activities.The growth of sacred painting in Ethiopia was a result of the introduction of Christianity in the 4th century AD.In addition the Ethiopian Orthodox Church approval of using paintings as a medium of teaching contributed for this development.Due to lack of evidences and insufficient researches conducted in the field little is known about ancient history of Ethiopian paintings.Most of the researches conducted focused on medieval period religious paintings and lately developed.The aim of this study is to investigate the development,significance,and challenges of churches with murals of the Gondarian painting style.The study was qualitative in approach and descriptive in design.In order to get valuable information for the study both primary and secondary sources were collected through interview,observation,and review of related literatures.And the data obtained through the above mentioned data gathering tools were analyzed qualitatively.The finding revealed that medieval period in Ethiopia witnessed the development of religious paintings mainly during the Gondarian period.Religious paintings of the period painted mainly on foundations of parchments,wall,and wood panel.Like other tourist attractions,wall paintings contributed a lot in attracting both domestic and international tourists.Due to several man-made and natural problems those wall paintings faced serious challenges which need an immediate intervention from the concerned bodies.
文摘The Mexican mural movement,also known as Mexican muralism,is recognized as one of the most significant art movements of the 20th century.It developed in the aftermath of the Mexican Revolution,which took place between 1910 and 1920.The country was striving to rebuild and unify after years of conflict,and muralism became a powerful tool for this transformation.
文摘In the thousand-year-old mural of Mogao Grottoes in Dunhuang,a special symbol tells the story of exchanges among civilisations.Three Rabbits Sharing Three Ears depicts three rabbits chasing each other,with each two sharing one ear.It is said that its earliest version appeared in Dunhuang in the 6th century,and it had travelled across the desert along the ancient Silk Road,over mountains and rivers,leaping onto British ceramic tiles,integrating into Egyptian pottery and jumping cross the clock faces of German churches.
基金supported by Ministry of Education in China Project of Humanities and Social Sciences(No.19YJC760012)Star of Innovation Project for Outstanding Graduate Students in Gansu Province(No.2022CXZX-546)。
文摘For the existing deep learning image restoration methods,the joint guidance of structure and texture information is not considered,which leads to structural disorder and texture blur in the restoration results.A generative adversarial mural inpainting algorithm based on structural and texture hybrid enhancement was proposed.Firstly,the structure guidance branch composed of dynamic convolution cascade was constructed to improve the expression ability of structure features,and the structure information was used to guide the encoder coding to enhance the edge contour information of the coding feature map.Then,the multi-granularity feature extraction module was designed to obtain the texture features of texture guided branches,and the multi-scale texture information was used to guide the decoder to reconstruct and repair,so as to improve the texture consistency of murals.Finally,skip connection was used to promote the feature sharing of structure and texture features,and the spectral-normalized PatchGAN discriminator was used to complete the mural restoration.The digital restoration experiment results of real Dunhuang murals showed that the proposed method was better than the comparison algorithms in both subjective and objective evaluation,and the restoration results were clearer and more natural.
基金supported by National Natural Science Foundation of China(No.61963023)Humanities and Social Sciences Youth Foundation of Ministry of Education(No.19YJC760012)Lanzhou Jiaotong University Basic Top-Notch Personnel Project(No.2022JC36).
文摘Sparse representation has been highly successful in various tasks related to image processing and computer vision.For ancient mural image inpainting,traditional group sparse representation models usually lead to structure blur and line discontinuity due to the construction of similarity group solely based on the Euclidean distance and the randomness of dictionary initialization.To address the aforementioned issues,an improved curvature Gabor transform and group sparse representation(CGabor-GSR)model for ancient Dunhuang mural inpainting is proposed.To begin with,mutual information is introduced to weight the Euclidean distance,and then the weighted Euclidean distance acts as a new standard of similarity group.Subsequently,to mitigate the randomness of dictionary initialization,a curvature Gabor wavelet transform is proposed to extract the features and initialize the feature dictionary with dimension reduction based on principal component analysis(PCA).Ultimately,singular value decomposition(SVD)and split Bregman iteration(SBI)can be used to resolve the CGabor-GSR model to reconstruct the mural images.Experimental results on Dunhuang mural inpainting demonstrate tha the proposed CGabor-GSR achieves a better performance than compared algorithms in both objective and visual evaluation.
基金supported by the Ministry of Education-China Mobile Communications (MCM20190701)。
文摘In the long history of more than 1 500 years,Dunhuang murals suffered from various deteriorations causing irreversible damage such as falling off,fading,and so on.However,the existing Dunhuang mural restoration methods are time-consuming and not feasible to facilitate cultural dissemination and permanent inheritance.Inspired by cultural computing using artificial intelligence,gated-convolution-based dehaze net(GD-Net) was proposed for Dunhuang mural refurbishment and comprehensive protection.First,a neural network with gated convolution was applied to restore the falling off areas of the mural to ensure the integrity of the mural content.Second,a dehaze network was applied to enhance image quality to cope with the fading of the mural.Besides,a Dunhuang mural dataset was presented to meet the needs of deep learning approach,containing 1 180 images from the Cave 290 and Cave 112 of the Mogao Grottoes.The experimental results demonstrate the effectiveness and superiority of GD-Net.
基金supported by Key Research and Development Plan of Ministry of Science and Technology(No.2023YFF0906200)Shaanxi Key Research and Development Plan(No.2018ZDXM-SF-093)+3 种基金Shaanxi Province Key Industrial Innovation Chain(Nos.S2022-YF-ZDCXL-ZDLGY-0093 and 2023-ZDLGY-45)Light of West China(No.XAB2022YN10)The China Postdoctoral Science Foundation(No.2023M740760)Shaanxi Key Research and Development Plan(No.2024SF-YBXM-678).
文摘Mural paintings hold significant historical information and possess substantial artistic and cultural value.However,murals are inevitably damaged by natural environmental factors such as wind and sunlight,as well as by human activities.For this reason,the study of damaged areas is crucial for mural restoration.These damaged regions differ significantly from undamaged areas and can be considered abnormal targets.Traditional manual visual processing lacks strong characterization capabilities and is prone to omissions and false detections.Hyperspectral imaging can reflect the material properties more effectively than visual characterization methods.Thus,this study employs hyperspectral imaging to obtain mural information and proposes a mural anomaly detection algorithm based on a hyperspectral multi-scale residual attention network(HM-MRANet).The innovations of this paper include:(1)Constructing mural painting hyperspectral datasets.(2)Proposing a multi-scale residual spectral-spatial feature extraction module based on a 3D CNN(Convolutional Neural Networks)network to better capture multiscale information and improve performance on small-sample hyperspectral datasets.(3)Proposing the Enhanced Residual Attention Module(ERAM)to address the feature redundancy problem,enhance the network’s feature discrimination ability,and further improve abnormal area detection accuracy.The experimental results show that the AUC(Area Under Curve),Specificity,and Accuracy of this paper’s algorithm reach 85.42%,88.84%,and 87.65%,respectively,on this dataset.These results represent improvements of 3.07%,1.11%and 2.68%compared to the SSRN algorithm,demonstrating the effectiveness of this method for mural anomaly detection.
文摘In order to solve the problem of the lack of ornamental value and research value of ancient mural paintings due to low resolution and fuzzy texture details,a super resolution(SR)method based on generative adduction network(GAN)was proposed.This method reconstructed the detail texture of mural image better.Firstly,in view of the insufficient utilization of shallow image features,information distillation blocks(IDB)were introduced to extract shallow image features and enhance the output results of the network behind.Secondly,residual dense blocks with residual scaling and feature fusion(RRDB-Fs)were used to extract deep image features,which removed the BN layer in the residual block that affected the quality of image generation,and improved the training speed of the network.Furthermore,local feature fusion and global feature fusion were applied in the generation network,and the features of different levels were merged together adaptively,so that the reconstructed image contained rich details.Finally,in calculating the perceptual loss,the brightness consistency between the reconstructed fresco and the original fresco was enhanced by using the features before activation,while avoiding artificial interference.The experimental results showed that the peak signal-to-noise ratio and structural similarity metrics were improved compared with other algorithms,with an improvement of 0.512 dB-3.016 dB in peak signal-to-noise ratio and 0.009-0.089 in structural similarity,and the proposed method had better visual effects.
