Hasil untuk "Conservation and restoration of prints"

Kazuho Funakawa, Toshihiro Sakamoto, Kohei Imamura et al.

Japan’s agricultural workforce is shrinking and aging, posing a significant social issue. Yet, fundamental analysis—quantifying and mapping where and how rapidly this demographic shift is progressing—have been lacking, largely due to extensive municipal boundary reorganizations in Japan. This study aimed to visualize and clarify the current demographic shifts by restoring temporal comparability through a stable spatial baseline: the “sub-municipalities.” Using Census of Agriculture and Forestry data for 2005, 2010, 2015, and 2020, we mapped two indicators for core agricultural workers: (i) the decline rate between 2005 and 2020, and (ii) the proportion of workers aged 75 years and above in 2020, revealing the regional landscape of workforce shrinkage and aging. We produced nationwide maps at the sub-municipality level, summarized land-type trends using generalized mixed models, and identified areas of extreme change using hotspot/coldspot analysis. The results revealed a nationwide downturn with pronounced spatial heterogeneity: the strongest declines were observed in mountainous and upland-dominated areas, whereas they tended to be more moderate in flatland paddy areas. Hotspots were scattered throughout the country, but were mainly located in areas with significant geographical constraints. Coldspots, representing modest growth, were identified around the Kinki and northern Kita-Kyushu metropolitan fringes. The aging rate was the highest in mountainous and paddy areas, whereas flatland and upland-dominated areas tended to be more resilient in this aspect. Aging hotspots aligned with the Tokai–Tosan Mountain belt and the Sanyo and San’in regions, whereas coldspots were observed in Hokkaido and Tohoku regions. Although we focused on the numerical and age composition of core agricultural workers, the approach can be generalized to other census indicators (e.g., sales, cultivated area, and production type), supporting locally adapted, evidence-based rural policy.

Giovanni Multari

The restoration of the Pirelli Skyscraper—necessitated after a notorious plane crash in 2002—became a key example of architectural intervention in modern architecture with heritage status. Even two decades after its completion, the process stands out for extraordinary research and analysis efforts—involving studying existing documentation, observing and measuring spaces, materials, and construction techniques. This ongoing investigation reaffirms that essentiality, as thought by Gio Ponti, remains a fundamental principle of architectural design until today. The intervention strategies of Corvino+Multari, accompanied by a technical and scientific team, have breathed life into Ponti’s masterpiece while stimulating a broader reflection on approaches to complex architectural monuments. Engaging critically with its architecture, the project positions itself between restoration and intervention, both philological in its approach and contemporary in spirit. The meticulous restoration of the curtain wall, fixtures, and mosaic tesserae exemplifies this.

Joan Casals Pañella, Marta Domènech, Sara Vima Grau et al.

El presente artículo plantea una reflexión en torno al legado arquitectónico residencial en Europa posterior a la Segunda Guerra Mundial, a través del estudio de la rehabilitación del edificio DeFlat Kleiburg, ubicado en el barrio Bijlmermeer de Ámsterdam (2017). En particular, se propone una revisión crítica sobre la obsolescencia de las grandes actuaciones residenciales modernas concebidas como respuesta a la necesidad de provisión masiva de vivienda en el período de posguerra, así como sobre las estrategias y motivaciones contemporáneas para su rehabilitación. El texto profundiza en el estudio de los debates y prácticas que entienden el entorno habitado como un componente crucial del patrimonio construido, subrayando la necesidad de preservar los conjuntos residenciales como instrumento para fortalecer la cohesión social. Asimismo, se analiza en detalle la transformación llevada a cabo en Kleiburg, basada en una estrategia de rehabilitación interior orientada a salvaguardar la composición, los acabados y la estructura original, al tiempo que promueve la flexibilidad funcional y la diversificación tipológica y de usos.

Yuka Nojo, Antoni B. Chan

BackgroundUnderstanding the cognitive mechanisms and decision-making processes involved in aesthetic judgement of visual art has become a growing focus in recent research. While eye movements have been strongly associated with impression evaluations, the underlying processes linking gaze behaviour and aesthetic experience remain underexplored. Recent discourse suggests that compositional strategies in artworks may guide viewers’ gaze and support narrative understanding.ObjectiveWe hypothesised that the more closely a viewer’s gaze follows the artist’s intended compositional path, the better they comprehend the artwork’s intention and context, thereby enriching their aesthetic experience. This process is defined as RAIC (Reading an Artist’s Intention from the Composition).MethodsWe collected 30-s eye-tracking data from 48 participants who viewed 12 Japanese woodblock landscape prints (Ukiyo-e). These artworks were selected from a preliminary study of 101 prints, based on the six highest and six lowest aesthetic ratings. Eye movements were segmented into 3-s intervals. Using the VBHEM algorithm, a variational Bayesian extension of the Eye Movement Hidden Markov Model (EMHMM), we evaluated the similarity between participants’ gaze sequences and expert-estimated scanpaths provided by specialists from the Japanese Painting Conservation and Restoration Laboratory of the Tokyo University of the Arts. Pupil size was analysed as an index of perceptual fluency.ResultsArtworks with compositional structures aligned with expert scanpaths enabled viewers to better interpret the artist’s intention, promoting deeper aesthetic engagement. Additionally, high-rated artworks elicited greater perceptual fluency.ConclusionThese findings support the RAIC hypothesis, suggesting that guided visual exploration facilitates interpretation of artistic intention and contributes to a more meaningful aesthetic experience.

Vidya Venkatesan, Aomawa L. Shields, Russell Deitrick et al.

Eccentric planets may spend a significant portion of their orbits at large distances from their host stars, where low temperatures can cause atmospheric CO2 to condense out onto the surface, similar to the polar ice caps on Mars. The radiative effects on the climates of these planets throughout their orbits would depend on the wavelength-dependent albedo of surface CO2 ice that may accumulate at or near apoastron and vary according to the spectral energy distribution of the host star. To explore these possible effects, we incorporated a CO2 ice-albedo parameterization into a one-dimensional energy balance climate model. With the inclusion of this parameterization, our simulations demonstrated that F-dwarf planets require 29% more orbit-averaged flux to thaw out of global water ice cover compared with simulations that solely use a traditional pure water ice-albedo parameterization. When no eccentricity is assumed, and host stars are varied, F-dwarf planets with higher bond albedos relative to their M-dwarf planet counterparts require 30% more orbit-averaged flux to exit a water snowball state. Additionally, the intense heat experienced at periastron aids eccentric planets in exiting a snowball state with a smaller increase in instellation compared with planets on circular orbits; this enables eccentric planets to exhibit warmer conditions along a broad range of instellation. This study emphasizes the significance of incorporating an albedo parameterization for the formation of CO2 ice into climate models to accurately assess the habitability of eccentric planets, as we show that, even at moderate eccentricities, planets with Earth-like atmospheres can reach surface temperatures cold enough for the condensation of CO2 onto their surfaces, as can planets receiving low amounts of instellation on circular orbits.

Bin Ren, Yawei Li, Xu Zheng et al.

Degradation-agnostic image restoration aims to handle diverse corruptions with one unified model, but faces fundamental challenges in balancing efficiency and performance across different degradation types. Existing approaches either sacrifice efficiency for versatility or fail to capture the distinct representational requirements of various degradations. We present MIRAGE, an efficient framework that addresses these challenges through two key innovations. First, we propose a channel-wise functional decomposition that systematically repurposes channel redundancy in attention mechanisms by assigning CNN, attention, and MLP branches to handle local textures, global context, and channel statistics, respectively. This principled decomposition enables degradation-agnostic learning while achieving superior efficiency-performance trade-offs. Second, we introduce manifold regularization that performs cross-layer contrastive alignment in Symmetric Positive Definite (SPD) space, which empirically improves feature consistency and generalization across degradation types. Extensive experiments demonstrate that MIRAGE achieves state-of-the-art performance with remarkable efficiency, outperforming existing methods in various all-in-one IR settings while offering a scalable and generalizable solution for challenging unseen IR scenarios.

Tianyu Zhang, Suyuchen Wang, Lu Li et al.

We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.

F. J. Alejandre Sánchez, C. Núñez Guerrero, S. Díaz Ramos et al.

Una manifestación artística de la decoración andalusí de la que se conservan escasos testimonios son los zócalos pintados en el ámbito doméstico. Los intentos por contextualizar estilística, geográfica y cronológicamente estos zócalos han planteado algunas cuestiones de índole tecnológica a la hora de apuntar posibles conexiones. El estudio de las técnicas de ejecución y materiales empleados en zócalos de Baŷŷāna (Almería), mediante análisis estratigráfico, DRX y FTIR, ha permitido establecer paralelismos con zócalos decorados procedentes del barrio de casas de la Alcazaba de Málaga a partir de una investigación anterior. Los resultados permiten extraer interesantes conclusiones sobre las técnicas de elaboración, que son congruentes con la pervivencia de algunos procedimientos de ejecución de los enlucidos de raigambre romana. Además, se plantea aquí la existencia de un núcleo de producción que agruparía los ejemplos provenientes de Almería y Málaga, cuyo contexto técnico los diferenciaría.

Shashank Agnihotri, Kanchana Vaishnavi Gandikota, Julia Grabinski et al.

Following their success in visual recognition tasks, Vision Transformers(ViTs) are being increasingly employed for image restoration. As a few recent works claim that ViTs for image classification also have better robustness properties, we investigate whether the improved adversarial robustness of ViTs extends to image restoration. We consider the recently proposed Restormer model, as well as NAFNet and the "Baseline network" which are both simplified versions of a Restormer. We use Projected Gradient Descent (PGD) and CosPGD, a recently proposed adversarial attack tailored to pixel-wise prediction tasks for our robustness evaluation. Our experiments are performed on real-world images from the GoPro dataset for image deblurring. Our analysis indicates that contrary to as advocated by ViTs in image classification works, these models are highly susceptible to adversarial attacks. We attempt to improve their robustness through adversarial training. While this yields a significant increase in robustness for Restormer, results on other networks are less promising. Interestingly, the design choices in NAFNet and Baselines, which were based on iid performance, and not on robust generalization, seem to be at odds with the model robustness. Thus, we investigate this further and find a fix.

Lily Xu, Esther Rolf, Sara Beery et al.

In this white paper, we synthesize key points made during presentations and discussions from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for Research on Computation and Society at Harvard University on October 20-21, 2022. We identify key open research questions in resource allocation, planning, and interventions for biodiversity conservation, highlighting conservation challenges that not only require AI solutions, but also require novel methodological advances. In addition to providing a summary of the workshop talks and discussions, we hope this document serves as a call-to-action to orient the expansion of algorithmic decision-making approaches to prioritize real-world conservation challenges, through collaborative efforts of ecologists, conservation decision-makers, and AI researchers.

Andrii Voshchepynets, Oleksiy Agapitov, Lynn Wilson et al.

We present the results of processing the effects of the powerful Gamma Ray Burst GRB221009A captured by the charged particle detectors (electrostatic analyzers and solid-state detectors) onboard spacecraft at different points in the heliosphere on October 9, 2022. To follow the GRB221009A propagation through the heliosphere we used the electron and proton flux measurements from solar missions Solar Orbiter and STEREO-A; Earth magnetosphere and the solar wind missions THEMIS and Wind; meteorological satellites POES15, POES19, MetOp3; and MAVEN - a NASA mission orbiting Mars. GRB221009A had a structure of four bursts: less intense Pulse 1 - the triggering impulse - was detected by gamma-ray observatories at 131659 UT (near the Earth); the most intense Pulses 2 and 3 were detected on board all the spacecraft from the list, and Pulse 4 detected in more than 500 s after Pulse 1. Due to their different scientific objectives, the spacecraft, which data was used in this study, were separated by more than 1 AU (Solar Orbiter and MAVEN). This enabled tracking GRB221009A as it was propagating across the heliosphere. STEREO-A was the first to register Pulse 2 and 3 of the GRB, almost 100 seconds before their detection by spacecraft in the vicinity of Earth. MAVEN detected GRB221009A Pulses 2, 3, and 4 at the orbit of Mars about 237 seconds after their detection near Earth. By processing the time delays observed we show that the source location of the GRB221009A was at RA 288.5 degrees, Dec 18.5 degrees (J2000) with an error cone of 2 degrees

Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao et al.

This work aims to improve the applicability of diffusion models in realistic image restoration. Specifically, we enhance the diffusion model in several aspects such as network architecture, noise level, denoising steps, training image size, and optimizer/scheduler. We show that tuning these hyperparameters allows us to achieve better performance on both distortion and perceptual scores. We also propose a U-Net based latent diffusion model which performs diffusion in a low-resolution latent space while preserving high-resolution information from the original input for the decoding process. Compared to the previous latent-diffusion model which trains a VAE-GAN to compress the image, our proposed U-Net compression strategy is significantly more stable and can recover highly accurate images without relying on adversarial optimization. Importantly, these modifications allow us to apply diffusion models to various image restoration tasks, including real-world shadow removal, HR non-homogeneous dehazing, stereo super-resolution, and bokeh effect transformation. By simply replacing the datasets and slightly changing the noise network, our model, named Refusion, is able to deal with large-size images (e.g., 6000 x 4000 x 3 in HR dehazing) and produces good results on all the above restoration problems. Our Refusion achieves the best perceptual performance in the NTIRE 2023 Image Shadow Removal Challenge and wins 2nd place overall.

Jing Lin, Xiaowan Hu, Yuanhao Cai et al.

How to properly model the inter-frame relation within the video sequence is an important but unsolved challenge for video restoration (VR). In this work, we propose an unsupervised flow-aligned sequence-to-sequence model (S2SVR) to address this problem. On the one hand, the sequence-to-sequence model, which has proven capable of sequence modeling in the field of natural language processing, is explored for the first time in VR. Optimized serialization modeling shows potential in capturing long-range dependencies among frames. On the other hand, we equip the sequence-to-sequence model with an unsupervised optical flow estimator to maximize its potential. The flow estimator is trained with our proposed unsupervised distillation loss, which can alleviate the data discrepancy and inaccurate degraded optical flow issues of previous flow-based methods. With reliable optical flow, we can establish accurate correspondence among multiple frames, narrowing the domain difference between 1D language and 2D misaligned frames and improving the potential of the sequence-to-sequence model. S2SVR shows superior performance in multiple VR tasks, including video deblurring, video super-resolution, and compressed video quality enhancement. Code and models are publicly available at https://github.com/linjing7/VR-Baseline

Zhuo Deng, Yuanhao Cai, Lu Chen et al.

Ophthalmologists have used fundus images to screen and diagnose eye diseases. However, different equipments and ophthalmologists pose large variations to the quality of fundus images. Low-quality (LQ) degraded fundus images easily lead to uncertainty in clinical screening and generally increase the risk of misdiagnosis. Thus, real fundus image restoration is worth studying. Unfortunately, real clinical benchmark has not been explored for this task so far. In this paper, we investigate the real clinical fundus image restoration problem. Firstly, We establish a clinical dataset, Real Fundus (RF), including 120 low- and high-quality (HQ) image pairs. Then we propose a novel Transformer-based Generative Adversarial Network (RFormer) to restore the real degradation of clinical fundus images. The key component in our network is the Window-based Self-Attention Block (WSAB) which captures non-local self-similarity and long-range dependencies. To produce more visually pleasant results, a Transformer-based discriminator is introduced. Extensive experiments on our clinical benchmark show that the proposed RFormer significantly outperforms the state-of-the-art (SOTA) methods. In addition, experiments of downstream tasks such as vessel segmentation and optic disc/cup detection demonstrate that our proposed RFormer benefits clinical fundus image analysis and applications. The dataset, code, and models are publicly available at https://github.com/dengzhuo-AI/Real-Fundus

Ruicheng Feng, Chongyi Li, Shangchen Zhou et al.

Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). To bridge the gap, we introduce the first MIPI challenge including five tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Under-Display Camera (UDC) Image Restoration track on MIPI 2022. In total, 167 participants were successfully registered, and 19 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Under-Display Camera Image Restoration. A detailed description of all models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://github.com/mipi-challenge/MIPI2022.

Edward J. Gillis

The assumption that wave function collapse is induced by correlating interactions of the kind that constitute measurements leads to a stochastic collapse equation that does not require the introduction of any new physical constants and that is consistent with conservation laws. The collapse operator is based on the interaction (potential) energy, with a variable timing parameter related to the rate at which individual interactions generate the correlations. The approximate localization of physical systems follows from the distance-dependent nature of the interaction potentials. The equation is consistent with strict conservation of momentum and orbital angular momentum, and it is also consistent with energy conservation within the accuracy allowed by the limited forms of energy that can be described within nonrelativistic theory. The possibility of extending the proposal to a fully relativistic version is discussed.

A. C. Umuhire, J. Uwamahoro, K. Sasikumar Raja et al.

Solar radio type II bursts serve as early indicators of incoming geo-effective space weather events such as coronal mass ejections (CMEs). In order to investigate the origin of high-frequency type II bursts (HF type II bursts), we have identified 51 of them (among 180 type II bursts from SWPC reports) that are observed by ground-based Compound Astronomical Low-cost Low-frequency Instrument for Spectroscopy and Transportable Observatory (CALLISTO) spectrometers and whose upper-frequency cutoff (of either fundamental or harmonic emission) lies in between 150 MHz-450 MHz during 2010-2019. We found that 60% of HF type II bursts, whose upper-frequency cutoff $\geq$ 300 MHz originate from the western longitudes. Further, our study finds a good correlation $\sim $ 0.73 between the average shock speed derived from the radio dynamic spectra and the corresponding speed from CME data. Also, we found that analyzed HF type II bursts are associated with wide and fast CMEs located near the solar disk. In addition, we have analyzed the spatio-temporal characteristics of two of these high-frequency type II bursts and compared the derived from radio observations with those derived from multi-spacecraft CME observations from SOHO/LASCO and STEREO coronagraphs.

Xingang Pan, Xiaohang Zhan, Bo Dai et al.

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semantics including color, spatial coherence, textures, and high-level concepts. This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images. As shown in Fig.1, the deep generative prior (DGP) provides compelling results to restore missing semantics, e.g., color, patch, resolution, of various degraded images. It also enables diverse image manipulation including random jittering, image morphing, and category transfer. Such highly flexible restoration and manipulation are made possible through relaxing the assumption of existing GAN-inversion methods, which tend to fix the generator. Notably, we allow the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN. We show that these easy-to-implement and practical changes help preserve the reconstruction to remain in the manifold of nature image, and thus lead to more precise and faithful reconstruction for real images. Code is available at https://github.com/XingangPan/deep-generative-prior.

Xintao Wang, Kelvin C. K. Chan, Ke Yu et al.

Video restoration tasks, including super-resolution, deblurring, etc, are drawing increasing attention in the computer vision community. A challenging benchmark named REDS is released in the NTIRE19 Challenge. This new benchmark challenges existing methods from two aspects: (1) how to align multiple frames given large motions, and (2) how to effectively fuse different frames with diverse motion and blur. In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges. First, to handle large motions, we devise a Pyramid, Cascading and Deformable (PCD) alignment module, in which frame alignment is done at the feature level using deformable convolutions in a coarse-to-fine manner. Second, we propose a Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration. Thanks to these modules, our EDVR wins the champions and outperforms the second place by a large margin in all four tracks in the NTIRE19 video restoration and enhancement challenges. EDVR also demonstrates superior performance to state-of-the-art published methods on video super-resolution and deblurring. The code is available at https://github.com/xinntao/EDVR.

Yuan Liu, Zhongwei Cheng, Jie Liu et al.

Saving rainforests is a key to halting adverse climate changes. In this paper, we introduce an innovative solution built on acoustic surveillance and machine learning technologies to help rainforest conservation. In particular, We propose new convolutional neural network (CNN) models for environmental sound classification and achieved promising preliminary results on two datasets, including a public audio dataset and our real rainforest sound dataset. The proposed audio classification models can be easily extended in an automated machine learning paradigm and integrated in cloud-based services for real world deployment.