Hasil untuk "Conservation and restoration of prints"

Kai Guan, Rongyuan Wu, Shuai Li et al.

In real-world scenarios, the performance of semantic segmentation often deteriorates when processing low-quality (LQ) images, which may lack clear semantic structures and high-frequency details. Although image restoration techniques offer a promising direction for enhancing degraded visual content, conventional real-world image restoration (Real-IR) models primarily focus on pixel-level fidelity and often fail to recover task-relevant semantic cues, limiting their effectiveness when directly applied to downstream vision tasks. Conversely, existing segmentation models trained on high-quality data lack robustness under real-world degradations. In this paper, we propose Restoration Adaptation for Semantic Segmentation (RASS), which effectively integrates semantic image restoration into the segmentation process, enabling high-quality semantic segmentation on the LQ images directly. Specifically, we first propose a Semantic-Constrained Restoration (SCR) model, which injects segmentation priors into the restoration model by aligning its cross-attention maps with segmentation masks, encouraging semantically faithful image reconstruction. Then, RASS transfers semantic restoration knowledge into segmentation through LoRA-based module merging and task-specific fine-tuning, thereby enhancing the model's robustness to LQ images. To validate the effectiveness of our framework, we construct a real-world LQ image segmentation dataset with high-quality annotations, and conduct extensive experiments on both synthetic and real-world LQ benchmarks. The results show that SCR and RASS significantly outperform state-of-the-art methods in segmentation and restoration tasks. Code, models, and datasets will be available at https://github.com/Ka1Guan/RASS.git.

Xingyu Jiang, Ning Gao, Xiuhui Zhang et al.

Due to adverse atmospheric and imaging conditions, natural images suffer from various degradation phenomena. Consequently, image restoration has emerged as a key solution and garnered substantial attention. Although recent Transformer architectures have demonstrated impressive success across various restoration tasks, their considerable model complexity poses significant challenges for both training and real-time deployment. Furthermore, instead of investigating the commonalities among different degradations, most existing restoration methods focus on modifying Transformer under limited restoration priors. In this work, we first review various degradation phenomena under multi-domain perspective, identifying common priors. Then, we introduce a novel restoration framework, which integrates multi-domain learning into Transformer. Specifically, in Token Mixer, we propose a Spatial-Wavelet-Fourier multi-domain structure that facilitates local-region-global multi-receptive field modeling to replace vanilla self-attention. Additionally, in Feed-Forward Network, we incorporate multi-scale learning to fuse multi-domain features at different resolutions. Comprehensive experimental results across ten restoration tasks, such as dehazing, desnowing, motion deblurring, defocus deblurring, rain streak/raindrop removal, cloud removal, shadow removal, underwater enhancement and low-light enhancement, demonstrate that our proposed model outperforms state-of-the-art methods and achieves a favorable trade-off among restoration performance, parameter size, computational cost and inference latency. The code is available at: https://github.com/deng-ai-lab/SWFormer.

Hao Yang, Yan Yang, Ruikun Zhang et al.

Recent advances in OpenAI's GPT-series multimodal generation models have shown remarkable capabilities in producing visually compelling images. In this work, we investigate its potential impact on the image restoration community. We provide, to the best of our knowledge, the first systematic benchmark across diverse restoration scenarios. Our evaluation shows that, while the restoration results generated by GPT-Image models are often perceptually pleasant, they tend to lack pixel-level structural fidelity compared with ground-truth references. Typical deviations include changes in image geometry, object positions or counts, and even modifications in perspective. Beyond empirical observations, we further demonstrate that outputs from GPT-Image models can act as strong visual priors, offering notable performance improvements for existing restoration networks. Using dehazing, deraining, and low-light enhancement as representative case studies, we show that integrating GPT-generated priors significantly boosts restoration quality. This study not only provides practical insights and a baseline framework for incorporating GPT-based generative priors into restoration pipelines, but also highlights new opportunities for bridging image generation models and restoration tasks. To support future research, we will release GPT-restored results.

Hernán A. Elgueta Strange, Jing Chang Lou

Recuperar el patrimonio arquitectónico enfrenta desafíos cuando las edificaciones son vulnerables a riesgos naturales. El Lazareto San Vicente de Paul en Santiago de Chile fue construido entre 1872 y 1875 con muros de albañilería simple de ladrillo y techumbre abovedada de madera formando cúpulas encamonadas. Dada la amenaza sísmica, su intervención contempló conservar el máximo de elementos originales, limitando las reconstrucciones a lo esencial para asegurar la estabilidad estructural y durabilidad del edificio. El texto reflexiona sobre la optimización de estrategias de intervención desde el punto de vista técnico y estético, de acuerdo con las características y valores del edificio.

Irene Ontiveros Llorens

El patrimonio arquitectónico ha adquirido una creciente relevancia como testimonio cultural y expresión de la identidad colectiva. Su rehabilitación y reutilización representan una oportunidad única para preservar su valor, incluyendo tanto monumentos icónicos como tejidos urbanos. Sin embargo, la arquitectura vernácula continúa siendo subestimada, lo que evidencia la necesidad de articular la protección del legado urbano con un enfoque que también incluya la arquitectura humilde tradicional. En el ámbito educativo, el patrimonio se presenta como un recurso pedagógico eficaz para construir identidad. Pese a los avances legislativos y metodológicos, persiste una visión limitada que continúa descuidando algo tan esencial para la formación integral como es la educación artística, cuando ésta resulta fundamental para alinear la enseñanza con directrices globales como la Agenda 2030 (ONU) y promover la sostenibilidad, el desarrollo social y la implicación del alumnado en la valoración y conservación del patrimonio.

Conghan Yue, Zhengwei Peng, Junlong Ma et al.

Image restoration refers to the process of restoring a damaged low-quality image back to its corresponding high-quality image. Typically, we use convolutional neural networks to directly learn the mapping from low-quality images to high-quality images achieving image restoration. Recently, a special type of diffusion bridge model has achieved more advanced results in image restoration. It can transform the direct mapping from low-quality to high-quality images into a diffusion process, restoring low-quality images through a reverse process. However, the current diffusion bridge restoration models do not emphasize the idea of conditional control, which may affect performance. This paper introduces the ECDB model enhancing the control of the diffusion bridge with low-quality images as conditions. Moreover, in response to the characteristic of diffusion models having low denoising level at larger values of \(\bm t \), we also propose a Conditional Fusion Schedule, which more effectively handles the conditional feature information of various modules. Experimental results prove that the ECDB model has achieved state-of-the-art results in many image restoration tasks, including deraining, inpainting and super-resolution. Code is avaliable at https://github.com/Hammour-steak/ECDB.

Marcos V. Conde, Gregor Geigle, Radu Timofte

Image restoration is a fundamental problem that involves recovering a high-quality clean image from its degraded observation. All-In-One image restoration models can effectively restore images from various types and levels of degradation using degradation-specific information as prompts to guide the restoration model. In this work, we present the first approach that uses human-written instructions to guide the image restoration model. Given natural language prompts, our model can recover high-quality images from their degraded counterparts, considering multiple degradation types. Our method, InstructIR, achieves state-of-the-art results on several restoration tasks including image denoising, deraining, deblurring, dehazing, and (low-light) image enhancement. InstructIR improves +1dB over previous all-in-one restoration methods. Moreover, our dataset and results represent a novel benchmark for new research on text-guided image restoration and enhancement. Our code, datasets and models are available at: https://github.com/mv-lab/InstructIR

Siyang Wang, Feng Zhao

Generative models trained on extensive high-quality datasets effectively capture the structural and statistical properties of clean images, rendering them powerful priors for transforming degraded features into clean ones in image restoration. VAR, a novel image generative paradigm, surpasses diffusion models in generation quality by applying a next-scale prediction approach. It progressively captures both global structures and fine-grained details through the autoregressive process, consistent with the multi-scale restoration principle widely acknowledged in the restoration community. Furthermore, we observe that during the image reconstruction process utilizing VAR, scale predictions automatically modulate the input, facilitating the alignment of representations at subsequent scales with the distribution of clean images. To harness VAR's adaptive distribution alignment capability in image restoration tasks, we formulate the multi-scale latent representations within VAR as the restoration prior, thus advancing our delicately designed VarFormer framework. The strategic application of these priors enables our VarFormer to achieve remarkable generalization on unseen tasks while also reducing training computational costs. Extensive experiments underscores that our VarFormer outperforms existing multi-task image restoration methods across various restoration tasks.

Chu-Jie Qin, Rui-Qi Wu, Zikun Liu et al.

All-in-one image restoration aims to handle multiple degradation types using one model. This paper proposes a simple pipeline for all-in-one blind image restoration to Restore Anything with Masks (RAM). We focus on the image content by utilizing Mask Image Modeling to extract intrinsic image information rather than distinguishing degradation types like other methods. Our pipeline consists of two stages: masked image pre-training and fine-tuning with mask attribute conductance. We design a straightforward masking pre-training approach specifically tailored for all-in-one image restoration. This approach enhances networks to prioritize the extraction of image content priors from various degradations, resulting in a more balanced performance across different restoration tasks and achieving stronger overall results. To bridge the gap of input integrity while preserving learned image priors as much as possible, we selectively fine-tuned a small portion of the layers. Specifically, the importance of each layer is ranked by the proposed Mask Attribute Conductance (MAC), and the layers with higher contributions are selected for finetuning. Extensive experiments demonstrate that our method achieves state-of-the-art performance. Our code and model will be released at \href{https://github.com/Dragonisss/RAM}{https://github.com/Dragonisss/RAM}.

Yang Zhao, Tingbo Hou, Yu-Chuan Su et al.

An authentic face restoration system is becoming increasingly demanding in many computer vision applications, e.g., image enhancement, video communication, and taking portrait. Most of the advanced face restoration models can recover high-quality faces from low-quality ones but usually fail to faithfully generate realistic and high-frequency details that are favored by users. To achieve authentic restoration, we propose $\textbf{IDM}$, an $\textbf{I}$teratively learned face restoration system based on denoising $\textbf{D}$iffusion $\textbf{M}$odels (DDMs). We define the criterion of an authentic face restoration system, and argue that denoising diffusion models are naturally endowed with this property from two aspects: intrinsic iterative refinement and extrinsic iterative enhancement. Intrinsic learning can preserve the content well and gradually refine the high-quality details, while extrinsic enhancement helps clean the data and improve the restoration task one step further. We demonstrate superior performance on blind face restoration tasks. Beyond restoration, we find the authentically cleaned data by the proposed restoration system is also helpful to image generation tasks in terms of training stabilization and sample quality. Without modifying the models, we achieve better quality than state-of-the-art on FFHQ and ImageNet generation using either GANs or diffusion models.

Hu Gao, Depeng Dang

Image restoration is a long-standing low-level vision problem, e.g., deblurring and deraining. In the process of image restoration, it is necessary to consider not only the spatial details and contextual information of restoration to ensure the quality, but also the system complexity. Although many methods have been able to guarantee the quality of image restoration, the system complexity of the state-of-the-art (SOTA) methods is increasing as well. Motivated by this, we present a mixed hierarchy network that can balance these competing goals. Our main proposal is a mixed hierarchy architecture, that progressively recovers contextual information and spatial details from degraded images while we design intra-blocks to reduce system complexity. Specifically, our model first learns the contextual information using encoder-decoder architectures, and then combines them with high-resolution branches that preserve spatial detail. In order to reduce the system complexity of this architecture for convenient analysis and comparison, we replace or remove the nonlinear activation function with multiplication and use a simple network structure. In addition, we replace spatial convolution with global self-attention for the middle block of encoder-decoder. The resulting tightly interlinked hierarchy architecture, named as MHNet, delivers strong performance gains on several image restoration tasks, including image deraining, and deblurring.

Zhenqi He, Junjun He, Jin Ye et al.

Histological whole slide images (WSIs) can be usually compromised by artifacts, such as tissue folding and bubbles, which will increase the examination difficulty for both pathologists and Computer-Aided Diagnosis (CAD) systems. Existing approaches to restoring artifact images are confined to Generative Adversarial Networks (GANs), where the restoration process is formulated as an image-to-image transfer. Those methods are prone to suffer from mode collapse and unexpected mistransfer in the stain style, leading to unsatisfied and unrealistic restored images. Innovatively, we make the first attempt at a denoising diffusion probabilistic model for histological artifact restoration, namely ArtiFusion.Specifically, ArtiFusion formulates the artifact region restoration as a gradual denoising process, and its training relies solely on artifact-free images to simplify the training complexity.Furthermore, to capture local-global correlations in the regional artifact restoration, a novel Swin-Transformer denoising architecture is designed, along with a time token scheme. Our extensive evaluations demonstrate the effectiveness of ArtiFusion as a pre-processing method for histology analysis, which can successfully preserve the tissue structures and stain style in artifact-free regions during the restoration. Code is available at https://github.com/zhenqi-he/ArtiFusion.

Cheng Zhang, Shaolin Su, Yu Zhu et al.

In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean results from the captured images heavily depends on the ability of restoration methods and the quality of the input. Although existing research on image restoration focuses on developing models for obtaining better restored results, fewer have studied to evaluate how and which input image leads to superior restored quality. In this paper, to better study an image's potential value that can be explored for restoration, we propose a novel concept, referring to image restoration potential (IRP). Specifically, We first establish a dynamic scene imaging dataset containing composite distortions and applied image restoration processes to validate the rationality of the existence to IRP. Based on this dataset, we investigate several properties of IRP and propose a novel deep model to accurately predict IRP values. By gradually distilling and selective fusing the degradation features, the proposed model shows its superiority in IRP prediction. Thanks to the proposed model, we are then able to validate how various image restoration related applications are benefited from IRP prediction. We show the potential usages of IRP as a filtering principle to select valuable frames, an auxiliary guidance to improve restoration models, and even an indicator to optimize camera settings for capturing better images under dynamic scenarios.

Amir A. Zadpoor

Mechanical metamaterials owe their extraordinary properties and functionalities to their micro-/nanoscale design of which shape, including both geometry and topology, is perhaps the most important aspect. 4D printing enables programmed, predictable, and precise change in the shape of mechanical metamaterials to achieve multi-functionality, adaptive properties, and the other types of desired behaviors that cannot be achieved using simple 3D printing. This paper presents an overview of 4D printing as applied to mechanical metamaterials. It starts by presenting a systematic definition of what 4D printing is and what shape aspects (e.g., geometry, topology) are relevant for the 4D printing of mechanical metamaterials. Instead of focusing on different printing processes and materials, the paper addresses the most fundamental aspects of the shapeshifting behaviors required for transforming a flat construct to a target 3D shape (i.e., 2D to 3D shapeshifting) or transforming a 3D shape to another 3D shape (i.e., 3D to 3D shapeshifting). In either case, we will discuss the rigid-body shape morphing (e.g., rigid origami) as well as deformable-body shapeshifting. The paper concludes with a discussion of the major challenges ahead of us for applying 4D printing to mechanical metamaterials and suggests several areas for future research.

Kotoko Hiraoka, Kensuke Fukumoto, Takashi Yamazoe et al.

We propose an efficient framework with compatibility between normal printing and printing with special color inks in this paper. Special color inks can be used for printing to represent some particular colors and specific optical properties, which are difficult to express using only CMYK inks. Special color layers are required in addition to the general color layer for printing with special color inks. We introduce a reversible data hiding (RDH) method to embed the special color layers into the general color layer without visible artifacts. The proposed method can realize both normal printing and printing with special color inks by using a single layer. Our experimental results show that the quality of the marked image is virtually identical to that of the original image, i.e., the general color layer.

Alexander Nettekoven, Ufuk Topcu

3D printing using robots has garnered significant interest in manufacturing and construction in recent years. A robot's versatility paired with the design freedom of 3D printing offers promising opportunities for how parts and structures are built in the future. However, 3D printed objects are still limited in size and location due to a lack of vertical mobility of ground robots. These limitations severely restrict the potential of the 3D printing process. To overcome these limitations, we develop a hexacopter testbed that can print via fused deposition modeling during flight. We discuss the design of this testbed and develop a simple control strategy for initial print tests. By successfully performing these initial print tests, we demonstrate the feasibility of this approach and lay the groundwork for printing 3D parts and structures with drones.

Chandantaru Dey Modak, Arvind Kumar, Abinash Tripathy et al.

Hydrodynamic collapse of a central air-cavity during the recoil phase of droplet impact on a superhydrophobic sieve leads to satellite-free generation of a single droplet through the sieve. Two modes of cavity formation and droplet ejection was observed and explained. The volume of the generated droplet scales with the pore size. Based on this phenomenon, we propose a new drop-on-demand printing technique. Despite significant advancements in inkjet technology, enhancement in mass-loading and particle-size have been limited due to clogging of the printhead nozzle. By replacing the nozzle with a sieve, we demonstrate printing of nanoparticle suspension with 71% mass-loading. Comparatively large particles of 20 micrometer diameter were dispensed in droplets of 80 micrometer diameter. Printing was performed for surface tension as low as 32 mNm-1 and viscosity as high as 33 mPa-s. In comparison to existing techniques, this new way of printing is widely accessible as it is significantly simple and economical.

Xinjie Lan, Xin Guo, Kenneth E. Barner

Deep Neural Networks (DNNs) have aroused great attention in Compressed Sensing (CS) restoration. However, the working mechanism of DNNs is not explainable, thereby it is unclear that how to design an optimal DNNs for CS restoration. In this paper, we propose a novel statistical framework to explain DNNs, which proves that the hidden layers of DNNs are equivalent to Gibbs distributions and interprets DNNs as a Bayesian hierarchical model. The framework provides a Bayesian perspective to explain the working mechanism of DNNs, namely some hidden layers learn a prior distribution and other layers learn a likelihood distribution. Moreover, the framework provides insights into DNNs and reveals two inherent limitations of DNNs for CS restoration. In contrast to most previous works designing an end-to-end DNNs for CS restoration, we propose a novel DNNs to model a prior distribution only, which can circumvent the limitations of DNNs. Given the prior distribution generated from the DNNs, we design a Bayesian inference algorithm to realize CS restoration in the framework of Bayesian Compressed Sensing. Finally, extensive simulations validate the proposed theory of DNNs and demonstrate that the proposed algorithm outperforms the state-of-the-art CS restoration methods.

José Luis Baró Zarzo, Miguel Ángel de Haro Muñoz

The small size of rural settlements, closely connected to the landscape, the constructive homogeneity of their architecture, their resilient tradition safeguarded by locals, and other singularities highlighted in protected settings suggest the need for a specific debate when intervening to bridge the voids which have appeared. This article aims to navigate this by examining interventions in the historic center of Albarracín (Teruel, Spain). Firstly, an assessment is carried out on the suitability or inconvenience of reconstructing on sites with limited past remains. Secondly, the way in which this void can be remedied is examined, between the need to be integrated to prevent distortions and the will to differ from this setting in order to prevent historical falsifications.

Christian Reul, Christoph Wick, Uwe Springmann et al.

A method is presented that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books when only small amounts of diplomatic transcriptions are available. This is achieved by building from already existing models during training instead of starting from scratch. To overcome the discrepancies between the set of characters of the pretrained model and the additional ground truth the OCRopus code is adapted to allow for alphabet expansion or reduction. The character set is now capable of flexibly adding and deleting characters from the pretrained alphabet when an existing model is loaded. For our experiments we use a self-trained mixed model on early Latin prints and the two standard OCRopus models on modern English and German Fraktur texts. The evaluation on seven early printed books showed that training from the Latin mixed model reduces the average amount of errors by 43% and 26%, respectively compared to training from scratch with 60 and 150 lines of ground truth, respectively. Furthermore, it is shown that even building from mixed models trained on data unrelated to the newly added training and test data can lead to significantly improved recognition results.