Image restoration aims to recover high quality images from inputs degraded by various factors, such as adverse weather, blur, or low light. While recent studies have shown remarkable progress across individual or unified restoration tasks, they still suffer from limited generalization and inefficiency when handling unknown or composite degradations. To address these limitations, we propose RAR, a Restore, Assess and Repeat process, that integrates Image Quality Assessment (IQA) and Image Restoration (IR) into a unified framework to iteratively and efficiently achieve high quality image restoration. Specifically, we introduce a restoration process that operates entirely in the latent domain to jointly perform degradation identification, image restoration, and quality verification. The resulting model is fully trainable end to end and allows for an all-in-one assess and restore approach that dynamically adapts the restoration process. Also, the tight integration of IQA and IR into a unified model minimizes the latency and information loss that typically arises from keeping the two modules disjoint, (e.g. during image and/or text decoding). Extensive experiments show that our approach consistent improvements under single, unknown and composite degradations, thereby establishing a new state-of-the-art.
Carol Christian, Antonella Nota, Noreen Grice
et al.
Astronomy, a captivating field that draws upon science, mathematics, and engineering, has traditionally relied on visual representations to convey the wonders of the cosmos. While this approach effectively engages the sighted population, the use of imagery can exclude individuals with blindness or visual impairment (B/VI). Astronomical research is incorporated into press releases, media, outreach efforts, and educational systems aimed at enhancing public interest and often skill in science, but visual materials can hamper a population with B/VI. This paper explores the potential of 3D printing as an assistive technology providing an alternative to imagery. We produced textured 3D prints of astronomical research data from the Hubble Space Telescope (HST). Useability assessment of materials is an important phase of production before integration into structured programs, and we used a multi-phased approach in our prior research to create and test appropriate textures for 3D astronomical prints. This paper describes the last step of reviewing our 3D prints through informal useability sessions with diverse individuals. The assessment indicated our 3D prints provide reliable, informative representations of astronomical data appropriate for public use especially for public information, outreach programs, and science education for individuals with BVI.
Este texto propone señalar dos maneras de comprender la intervención en el patrimonio arquitectónico según el pensamiento heideggeriano del útil o de la obra de arte. Si la arquitectura es considerada un utensilio, la rehabilitación consistirá en devolverle su condición instrumental, pero los útiles, cuando funcionan, pasan desapercibidos. Rehabilitar consistirá pues en conseguir que el útil desaparezca de nuevo. Una segunda forma de rehabilitación consistiría en intervenir en el patrimonio anónimo, en el sentido dado por Heidegger, elevándolo a la condición de obra de arte, que es lo que convierte la arquitectura en lugar de máxima visibilidad y atención.
Conservation and restoration of prints, Architectural drawing and design
This work aims to illustrate difficulties in conservation and intervention with regard to Carlo Scarpa’s exposed reinforced concrete, which is characterised by unique formal features. The case study of the Brion Tomb (1969-78), designed by Carlo Scarpa (1906-1978), is exceptional for its monumental character, along with its designer’s desire to envisage its ageing, but not its deterioration, over time. In this sense, the almost exclusive use of reinforced concrete for the building and the choice of certain experimental technical solutions place this architectural complex within the general context of problems related to the restoration of contemporary architecture, due to the theoretical and operational difficulties in defining interventions for its conservation. The restoration of this complex, which was completed in 2020, was an extraordinary opportunity to reflect on the methods and limits of conservation work, and to update technical capabilities to the current state of the art.
Conservation and restoration of prints, Architectural drawing and design
Sammy Florczak, Gabriel Groessbacher, Davide Ribezzi
et al.
We introduce Generative, Adaptive, Context-Aware 3D Printing (GRACE), a novel approach combining 3D imaging, computer vision, and parametric modelling to create tailored, context-aware geometries using volumetric additive manufacturing. GRACE rapidly and automatically generates complex structures capable of conforming directly around features ranging from cellular to macroscopic scales with minimal user intervention. We demonstrate its versatility in applications ranging from synthetic objects to biofabrication, including adaptive vascular-like geometries around cell-laden bioinks, resulting in improved functionality. GRACE also enables precise alignment of sequential prints, in addition to the detection and overprinting of opaque surfaces through shadow correction. Compatible with various printing modalities, GRACE transcends traditional additive manufacturing limitations, opening new avenues in tissue engineering and regenerative medicine.
In this work we present a large-scale dataset of \textit{Ukiyo-e} woodblock prints. Unlike previous works and datasets in the artistic domain that primarily focus on western art, this paper explores this pre-modern Japanese art form with the aim of broadening the scope for stylistic analysis and to provide a benchmark to evaluate a variety of art focused Computer Vision approaches. Our dataset consists of over $175.000$ prints with corresponding metadata (\eg artist, era, and creation date) from the 17th century to present day. By approaching stylistic analysis as a Multi-Task problem we aim to more efficiently utilize the available metadata, and learn more general representations of style. We show results for well-known baselines and state-of-the-art multi-task learning frameworks to enable future comparison, and to encourage stylistic analysis on this artistic domain.
Muhammad Zubair Khan, Oleg E. Peil, Apoorva Sharma
et al.
In the rapidly expanding field of two-dimensional materials, magnetic monolayers show great promise for the future applications in nanoelectronics, data storage, and sensing. The research in intrinsically magnetic two-dimensional materials mainly focuses on synthetic iodide and telluride based compounds, which inherently suffer from the lack of ambient stability. So far, naturally occurring layered magnetic materials have been vastly overlooked. These minerals offer a unique opportunity to explore air-stable complex layered systems with high concentration of local moment bearing ions. We demonstrate magnetic ordering in iron-rich two-dimensional phyllosilicates, focusing on mineral species of minnesotaite, annite, and biotite. These are naturally occurring van der Waals magnetic materials which integrate local moment baring ions of iron via magnesium/aluminium substitution in their octahedral sites. Due to self-inherent capping by silicate/aluminate tetrahedral groups, ultra-thin layers are air-stable. Chemical characterization, quantitative elemental analysis, and iron oxidation states were determined via Raman spectroscopy, wavelength disperse X-ray spectroscopy, X-ray absorption spectroscopy, and X-ray photoelectron spectroscopy. Superconducting quantum interference device magnetometry measurements were performed to examine the magnetic ordering. These layered materials exhibit paramagnetic or superparamagnetic characteristics at room temperature. At low temperature ferrimagnetic or antiferromagnetic ordering occurs, with the critical ordering temperature of 38.7 K for minnesotaite, 36.1 K for annite, and 4.9 K for biotite. In-field magnetic force microscopy on iron bearing phyllosilicates confirmed the paramagnetic response at room temperature, present down to monolayers.
Pneumatic soft robots are typically fabricated by molding, a manual fabrication process that requires skilled labor. Additive manufacturing has the potential to break this limitation and speed up the fabrication process but struggles with consistently producing high-quality prints. We propose a low-cost approach to improve the print quality of desktop fused deposition modeling by adding a webcam to the printer to monitor the printing process and detect and correct defects such as holes or gaps. We demonstrate that our approach improves the air-tightness of printed pneumatic actuators without fine-tuning printing parameters. Our approach presents a new option for robustly fabricating airtight, soft robotic actuators.
Despite the decades-long history of 3D printing, it is not used to its full potential. Yet 3D printing holds promise for isolated communities, aiming for self-sufficiency. In this experiential study conducted in an analog space habitat we evaluated challenges and opportunities of using 3D printing. Our study revealed barriers such as: 1) setting up and maintaining the 3D printing equipment while minding different kinds of pollution, that is air, temperature and sound, 2) design skill and familiarity with specialized software as well as materials and 3) the awareness of what can be achieved to meet community needs. We observed that in-community experience and know-how are reliable sources of 3D print ideas, that improve quality of life of community members if they are encouraged and supported by participatory design. Co-design of 3D prints in small, specialized communities is a promising area of study, that can bring new applications of 3D print technology.
Recent image restoration methods have produced significant advancements using deep learning. However, existing methods tend to treat the whole image as a single entity, failing to account for the distinct objects in the image that exhibit individual texture properties. Existing methods also typically generate a single result, which may not suit the preferences of different users. In this paper, we introduce the Restore Anything Pipeline (RAP), a novel interactive and per-object level image restoration approach that incorporates a controllable model to generate different results that users may choose from. RAP incorporates image segmentation through the recent Segment Anything Model (SAM) into a controllable image restoration model to create a user-friendly pipeline for several image restoration tasks. We demonstrate the versatility of RAP by applying it to three common image restoration tasks: image deblurring, image denoising, and JPEG artifact removal. Our experiments show that RAP produces superior visual results compared to state-of-the-art methods. RAP represents a promising direction for image restoration, providing users with greater control, and enabling image restoration at an object level.
Facial landmark detection plays an important role for the similarity analysis in artworks to compare portraits of the same or similar artists. With facial landmarks, portraits of different genres, such as paintings and prints, can be automatically aligned using control-point-based image registration. We propose a deep-learning-based method for facial landmark detection in high-resolution images of paintings and prints. It divides the task into a global network for coarse landmark prediction and multiple region networks for precise landmark refinement in regions of the eyes, nose, and mouth that are automatically determined based on the predicted global landmark coordinates. We created a synthetically augmented facial landmark art dataset including artistic style transfer and geometric landmark shifts. Our method demonstrates an accurate detection of the inner facial landmarks for our high-resolution dataset of artworks while being comparable for a public low-resolution artwork dataset in comparison to competing methods.
The prioritization of restoration actions after large power system outages plays a key role in how quickly power can be restored. It has been shown that fast and intuitive heuristics for restoration prioritization most often result in low-quality restoration plans. Meanwhile, mathematical optimization tools that find high-quality restoration plans are too slow to be applied to restoration planning problems of practical interest. This work makes a significant step in closing this quality vs compute time gap by proposing the Recursive Restoration Refinement heuristic for power system restoration. This heuristic is shown to produce near-optimal restoration plans up to 1,000 times faster than other state-of-the-art solution methods on a range of test cases with up to 500 buses and 700 damaged components. The potential impact of this new heuristic is demonstrated by a preliminary analysis of the key features of high-quality restoration plans. The recursive restoration refinement algorithm and other methods explored in this work have been made available as part of the open-source software package, PowerModelsRestoration, to support ongoing research in power restoration algorithms.
Ayako Yoshino, Akinori Takami, Keiichiro Hara
et al.
Transboundary air pollution (TAP) and local air pollution (LAP) influence the air quality of urban areas. Fukuoka, located on the west side of Japan and affected by TAP from the Asian continent, is a unique example for understanding the contribution of LAP and TAP. Gaseous species and particulate matter (PM) were measured for approximately three weeks in Fukuoka in the winter of 2018. We classified two distinctive periods, LAP and TAP, based on wind speed. The classification was supported by variations in the concentration of gaseous species and by backward trajectories. Most air pollutants, including NOx and PM, were high in the LAP period and low in the TAP period. However, ozone was the exception. Therefore, our findings suggest that reducing local emissions is necessary. Ozone was higher in the TAP period, and the variation in ozone concentration was relatively small, indicating that ozone was produced outside of the city and transported to Fukuoka. Thus, air pollutants must also be reduced at a regional scale, including in China.
Between 2020 and 2021, the world was paralyzed due to the COVID-19 Pandemic. Concurrently, the devastating effects of Greenhouse Gases, the cause of the drastic Climate Change that threatens us, were considerably reduced. Nature had a well-deserved respite when we were locked-up and immobile, and the architectural heritage was protected by stabilizing the drastic changes in the climate. Are we the protagonists of the devastation of the planet and consequently, of the destruction of our architectural heritage? The intervention processes for existing structures must respond, in a compatible way, to their particular building technologies and their geographical location. If the only “green” building is that which already exists, the recycling of its components and recovery are sustainable techniques that our ancestors used as a conscious process to protect, and not waste, the natural resources of our planet earth necessary for their survival.
Conservation and restoration of prints, Architectural drawing and design
Arnaud Mazier, Alexandre Bilger, Antonio E. Forte
et al.
In this paper, we develop a framework for solving inverse deformation problems using the FEniCS Project finite element software. We validate our approach with experimental imaging data acquired from a soft silicone beam under gravity. In contrast with inverse iterative algorithms that require multiple solutions of a standard elasticity problem, the proposed method can compute the undeformed configuration by solving only one modified elasticity problem. This modified problem has a complexity comparable to the standard one. The framework is implemented within an open-source pipeline enabling the direct and inverse deformation simulation directly from imaging data. We use the high-level Unified Form Language (UFL) of the FEniCS Project to express the finite element model in variational form and to automatically derive the consistent Jacobian. Consequently, the design of the pipeline is flexible: for example, it allows the modification of the constitutive models by changing a single line of code. We include a complete working example showing the inverse deformation of a beam deformed by gravity as supplementary material.