This work proposes a green learning (GL) approach to restore medical images. Without loss of generality, we use low-dose computed tomography (LDCT) images as examples. LDCT images are susceptible to noise and artifacts, where the imaging process introduces distortion. LDCT image restoration is an important preprocessing step for further medical analysis. Deep learning (DL) methods have been developed to solve this problem. We examine an alternative solution using the Green Learning (GL) methodology. The new restoration method is characterized by mathematical transparency, computational and memory efficiency, and high performance. Experiments show that our GL method offers state-of-the-art restoration performance at a smaller model size and with lower inference complexity.
Federica Fernandez, Elvira Nicolini, Roberta Montagno
et al.
In this study, three water-based nanostructured protective coatings were tested on bricks from the Grand Continental Hotel in Cairo, partially demolished in 2017. The aim was to identify sustainable conservation strategies for bricks intended for reconstruction. The comparative evaluation, preceded by material characterization using XRF and XRD, included contact angle measurements, colorimetric analysis, and infrared spectroscopy. The coatings were assessed for water repellency and visual impact. Results show that P1, a fluorinated siloxane, ensured good protection without color change and allowed water runoff on inclined surfaces. P2 caused slight darkening, while P3 showed IR issues, excluding it from further use. All coatings, being water-based, are safer for the environment and restorers. This study supports informed product selection and offers a replicable model for sustainable heritage conservation in Egypt.
Conservation and restoration of prints, Architectural drawing and design
Muhammad Awais Amin, Adama Ilboudo, Abdul Samad bin Shahid
et al.
One of the major challenges in the field of computer vision especially for detection, segmentation, recognition, monitoring, and automated solutions, is the quality of images. Image degradation, often caused by factors such as rain, fog, lighting, etc., has a negative impact on automated decision-making.Furthermore, several image restoration solutions exist, including restoration models for single degradation and restoration models for multiple degradations. However, these solutions are not suitable for real-time processing. In this study, the aim was to develop a real-time image restoration solution for video surveillance. To achieve this, using transfer learning with ResNet_50, we developed a model for automatically identifying the types of degradation present in an image to reference the necessary treatment(s) for image restoration. Our solution has the advantage of being flexible and scalable.
Many image restoration (IR) tasks require both pixel-level fidelity and high-level semantic understanding to recover realistic photos with fine-grained details. However, previous approaches often struggle to effectively leverage both the visual and linguistic knowledge. Recent efforts have attempted to incorporate Vision-language models (VLMs), which excel at aligning visual and textual features, into universal IR. Nevertheless, these methods fail to utilize the linguistic priors to ensure semantic coherence during the restoration process. To address this issue, in this paper, we propose the Vision-Language Model Guided Image Restoration (VLMIR) framework, which leverages the rich vision-language priors of VLMs, such as CLIP, to enhance IR performance through improved visual perception and semantic understanding. Our approach consists of two stages: VLM-based feature extraction and diffusion-based image restoration. In the first stage, we extract complementary visual and linguistic representations of input images by condensing the visual perception and high-level semantic priors through VLMs. Specifically, we align the embeddings of captions from low-quality and high-quality images using a cosine similarity loss with LoRA fine-tuning, and employ a degradation predictor to decompose degradation and clean image content embeddings. These complementary visual and textual embeddings are then integrated into a diffusion-based model via cross-attention mechanisms for enhanced restoration. Extensive experiments and ablation studies demonstrate that VLMIR achieves superior performance across both universal and degradation-specific IR tasks, underscoring the critical role of integrated visual and linguistic knowledge from VLMs in advancing image restoration capabilities.
Ultra-high-definition (UHD) image restoration is vital for applications demanding exceptional visual fidelity, yet existing methods often face a trade-off between restoration quality and efficiency, limiting their practical deployment. In this paper, we propose TSFormer, an all-in-one framework that integrates \textbf{T}rusted learning with \textbf{S}parsification to boost both generalization capability and computational efficiency in UHD image restoration. The key is that only a small amount of token movement is allowed within the model. To efficiently filter tokens, we use Min-$p$ with random matrix theory to quantify the uncertainty of tokens, thereby improving the robustness of the model. Our model can run a 4K image in real time (40fps) with 3.38 M parameters. Extensive experiments demonstrate that TSFormer achieves state-of-the-art restoration quality while enhancing generalization and reducing computational demands. In addition, our token filtering method can be applied to other image restoration models to effectively accelerate inference and maintain performance.
Multi-task image restoration has gained significant interest due to its inherent versatility and efficiency compared to its single-task counterpart. However, performance decline is observed with an increase in the number of tasks, primarily attributed to the restoration model's challenge in handling different tasks with distinct natures at the same time. Thus, a perspective emerged aiming to explore the degradation-insensitive semantic commonalities among different degradation tasks. In this paper, we observe that the features of DINOv2 can effectively model semantic information and are independent of degradation factors. Motivated by this observation, we propose \mbox{\textbf{DINO-IR}}, a multi-task image restoration approach leveraging robust features extracted from DINOv2 to solve multi-task image restoration simultaneously. We first propose a pixel-semantic fusion (PSF) module to dynamically fuse DINOV2's shallow features containing pixel-level information and deep features containing degradation-independent semantic information. To guide the restoration model with the features of DINOv2, we develop a DINO-Restore adaption and fusion module to adjust the channel of fused features from PSF and then integrate them with the features from the restoration model. By formulating these modules into a unified deep model, we propose a DINO perception contrastive loss to constrain the model training. Extensive experimental results demonstrate that our DINO-IR performs favorably against existing multi-task image restoration approaches in various tasks by a large margin. The source codes and trained models will be made available.
Alba Soler Estrela, Luis Cortés Meseguer, Rafael Soler-Verdú
La iglesia de las Escuelas Pías destaca por las excepcionales dimensiones de su cúpula, de 24,5 m de diámetro interior. En el momento actual se enfrenta a problemas de conservación, que obligan a determinar las causas de la patología y propongan medidas correctoras. Analizados los documentos y el estudio histórico-arquitectónico, se ha procedido a una exhaustiva toma de datos que ha permitido no solo la definición geométrica, sino también constructiva de su estado actual. A partir de la evaluación inicial se proponen estudios específicos centrados en el comportamiento estructural y en la caracterización de materiales y técnicas constructivas. Como resultado se ha elaborado una propuesta de fases de intervención para su conservación y restauración integral, así como un plan de investigación para avanzar en el conocimiento técnico de su arquitectura.
Conservation and restoration of prints, Architectural drawing and design
We present an approach for automatic punctuation restoration with BERT models for English and Hungarian. For English, we conduct our experiments on Ted Talks, a commonly used benchmark for punctuation restoration, while for Hungarian we evaluate our models on the Szeged Treebank dataset. Our best models achieve a macro-averaged $F_1$-score of 79.8 in English and 82.2 in Hungarian. Our code is publicly available.
In this paper we report on the 3D printing and testing of the piezoelectric polymer polyvinylidene difluoride (PVDF). Samples of PVDF were fabricated using a fused deposition modeling (FDM) 3D printer and then activated using a corona poling process. The d33 piezoelectric coefficient, which is related to the overall piezoelectric performance, was experimentally measured using a d33 meter to be 6 pC/N. While less than commercially available PVDF fabricated using traditional techniques (which can have a d33 between 10 and 40 pC/N), the value of 6 pC/N achieved in this work is several orders of magnitude larger than comparable previously published results for 3D printed PVDF, and as a result represents a significant step in the 3D printing of piezoelectric polymers.
Biological conservation and ecological restoration differ in their motivations, objectives, and dominant concepts. These differences translate into a dichotomy between the two disciplines in academia, which we illustrate through a review of the scientific literature. Conversely, in practice, conservation and restoration are part of an environmental management continuum and are often used as complementary tools. While we found an increasing transdisciplinary trend in the literature, there is much room for improvement. Optimized implementation of conservation and restoration actions is critical for addressing the increasing pressures of global change and we propose steps to better integrate the two disciplines.
Augusto C. Valente, Cristina Wada, Deangela Neves
et al.
Efficient automated print defect mapping is valuable to the printing industry since such defects directly influence customer-perceived printer quality and manually mapping them is cost-ineffective. Conventional methods consist of complicated and hand-crafted feature engineering techniques, usually targeting only one type of defect. In this paper, we propose the first end-to-end framework to map print defects at pixel level, adopting an approach based on semantic segmentation. Our framework uses Convolutional Neural Networks, specifically DeepLab-v3+, and achieves promising results in the identification of defects in printed images. We use synthetic training data by simulating two types of print defects and a print-scan effect with image processing and computer graphic techniques. Compared with conventional methods, our framework is versatile, allowing two inference strategies, one being near real-time and providing coarser results, and the other focusing on offline processing with more fine-grained detection. Our model is evaluated on a dataset of real printed images.
Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinders its performance due to the lack of suitable denoiser prior. In order to push the limits of plug-and-play image restoration, we set up a benchmark deep denoiser prior by training a highly flexible and effective CNN denoiser. We then plug the deep denoiser prior as a modular part into a half quadratic splitting based iterative algorithm to solve various image restoration problems. We, meanwhile, provide a thorough analysis of parameter setting, intermediate results and empirical convergence to better understand the working mechanism. Experimental results on three representative image restoration tasks, including deblurring, super-resolution and demosaicing, demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state-of-the-art learning-based methods. The source code is available at https://github.com/cszn/DPIR.
Many image restoration techniques are highly dependent on the degradation used during training, and their performance declines significantly when applied to slightly different input. Blind and universal techniques attempt to mitigate this by producing a trained model that can adapt to varying conditions. However, blind techniques to date require prior knowledge of the degradation process, and assumptions regarding its parameter-space. In this paper we present the Self-Normalization Side-Chain (SCNC), a novel approach to blind universal restoration in which no prior knowledge of the degradation is needed. This module can be added to any existing CNN topology, and is trained along with the rest of the network in an end-to-end manner. The imaging parameters relevant to the task, as well as their dynamics, are deduced from the variety in the training data. We apply our solution to several image restoration tasks, and demonstrate that the SNSC encodes the degradation-parameters, improving restoration performance.
Practical Building Conservation is a ten volume series that offers comprehensive guidance on a wide range of materials, from glass, timber and metals, to historic concrete. Two foundation volumes frame the books on building materials. Conservation Basics describes the history of conservation, current legal practice and methodology. Building Environment defines the environmental factors affecting composite building systems and how good conservation repairs support sustainable practice. This article explores the genesis of the series, from five small books published in 1988, to the current series with over 5,000 pages. The new work illustrates the evolution of building conservation over recent decades, now promoting holistic interventions based on an assessment of significance, condition and risk. The series refers to conservation practice in England. However, much of the information provided is of generic nature, so is applicable to other contexts.
Conservation and restoration of prints, Architectural drawing and design
With the recent advances in deep neural networks, anomaly detection in multimedia has received much attention in the computer vision community. While reconstruction-based methods have recently shown great promise for anomaly detection, the information equivalence among input and supervision for reconstruction tasks can not effectively force the network to learn semantic feature embeddings. We here propose to break this equivalence by erasing selected attributes from the original data and reformulate it as a restoration task, where the normal and the anomalous data are expected to be distinguishable based on restoration errors. Through forcing the network to restore the original image, the semantic feature embeddings related to the erased attributes are learned by the network. During testing phases, because anomalous data are restored with the attribute learned from the normal data, the restoration error is expected to be large. Extensive experiments have demonstrated that the proposed method significantly outperforms several state-of-the-arts on multiple benchmark datasets, especially on ImageNet, increasing the AUROC of the top-performing baseline by 10.1%. We also evaluate our method on a real-world anomaly detection dataset MVTec AD and a video anomaly detection dataset ShanghaiTech.
The effective restoration of the U_{A}(1) symmetry is revisited by implementing the functional renormalization group approach combining with the 2+1 flavor Polyakov-loop quark-meson model. A temperature-dependent 't Hooft term is taken to imitate the restoration of the U_{A}(1) symmetry. Order parameters, meson spectrum and mixing angles, especially the pressure and the entropy density of the system are calculated to explore the effects of different U_{A}(1) symmetry restoration patterns. We show then that the temperature for the restoration of the U_{A}(1) symmetry is much higher than that for the chiral symmetry SU_{A}(3).
Image degradation due to atmospheric turbulence is common while capturing images at long ranges. To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image. The disentanglement is achieved by decomposing the distortion due to turbulence into blur and deformation components using deblur generator and deformation correction generator respectively. Two paths of restoration are implemented to regularize the disentanglement and generate two restored images from one degraded image. A fusion function combines the features of the restored images to reconstruct a sharp image with rich details. Adversarial and perceptual losses are added to reconstruct a sharp image and suppress the artifacts respectively. Extensive experiments demonstrate the effectiveness of the proposed restoration algorithm, which achieves satisfactory performance in face restoration and face recognition.