Continuous wave laser thermal restoration of oxidized lead-based pigments in mural paintings [PDF]
Appl. Phys. B 127, 162 (2021), 2021 Red lead and lead white are some of the most ancient and common pigments in mural paintings. However, they tend to blacken with time due to their oxidation to plattnerite (\b{eta}-PbO2). The possibility to induce the reconversion reactions by CW laser heating is hereby discussed.
arxiv +1 more source
Thermal Reconversion of Oxidised Lead White in Mural Paintings via a Massicot Intermediate [PDF]
, 2023 Lead white is the most ancient and common white pigment used in mural paintings. However, it tends to blacken with time due to its oxidation to plattnerite (\b{eta}-PbO2). Chemical treatments were used but they can put the pictorial layers supports at risks.
arxiv +1 more source
The MURALES survey. IV. Searching for nuclear outflows in 3C radio galaxies at z < 0.3 with MUSE observations [PDF]
A&A 653, A150 (2021), 2021 We analyze VLT/MUSE observations of 37 radio galaxies from the Third Cambridge catalogue (3C) with redshift $<$0.3 searching for nuclear outflows of ionized gas. These observations are part of the MURALES project (a MUse RAdio Loud Emission line Snapshot survey), whose main goal is to explore the feedback process in the most powerful radio-loud AGN. We
arxiv +1 more source
Multi-stage Progressive Reasoning for Dunhuang Murals Inpainting [PDF]
arXiv, 2023 Dunhuang murals suffer from fading, breakage, surface brittleness and extensive peeling affected by prolonged environmental erosion. Image inpainting techniques are widely used in the field of digital mural inpainting. Generally speaking, for mural inpainting tasks with large area damage, it is challenging for any image inpainting method. In this paper,
arxiv
A 3M-Hybrid Model for the Restoration of Unique Giant Murals: A Case Study on the Murals of Yongle Palace [PDF]
arXiv, 2023 The Yongle Palace murals, as valuable cultural heritage, have suffered varying degrees of damage, making their restoration of significant importance. However, the giant size and unique data of Yongle Palace murals present challenges for existing deep-learning based restoration methods: 1) The distinctive style introduces domain bias in traditional ...
arxiv
Dunhuang murals contour generation network based on convolution and self-attention fusion [PDF]
arXiv, 2022 Dunhuang murals are a collection of Chinese style and national style, forming a self-contained Chinese-style Buddhist art. It has very high historical and cultural value and research significance. Among them, the lines of Dunhuang murals are highly general and expressive.
arxiv
MURAL: Multimodal, Multitask Retrieval Across Languages [PDF]
arXiv, 2021 Both image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages. We use both types of pairs in MURAL (MUltimodal, MUltitask Representations Across Languages), a dual encoder that solves two tasks: 1) image-text matching and 2) translation pair matching.
arxiv
Line Drawing Guided Progressive Inpainting of Mural Damage [PDF]
arXiv, 2022 Mural image inpainting is far less explored compared to its natural image counterpart and remains largely unsolved. Most existing image-inpainting methods tend to take the target image as the only input and directly repair the damage to generate a visually plausible result.
arxiv
Pilgrimage to Pureland: Art, Perception and the Wutai Mural VR Reconstruction [PDF]
arXiv, 2023 Virtual reality (VR) supports audiences to engage with cultural heritage proactively. We designed an easy-to-access and guided Pilgrimage To Pureland VR reconstruction of Dunhuang Mogao Grottoes to offer the general public an accessible and engaging way to explore the Dunhuang murals.
arxiv
MuRAL: Multi-Scale Region-based Active Learning for Object Detection [PDF]
arXiv, 2023 Obtaining large-scale labeled object detection dataset can be costly and time-consuming, as it involves annotating images with bounding boxes and class labels. Thus, some specialized active learning methods have been proposed to reduce the cost by selecting either coarse-grained samples or fine-grained instances from unlabeled data for labeling ...
arxiv