Yoonmo Yang

Oil paintings represent significant cultural heritage, as they embody human creativity and historical narratives. The preservation of these invaluable artifacts requires effective maintenance practices to ensure their longevity and integrity. Despite their inherent durability, oil paintings are susceptible to mechanical damage and chemical deterioration, necessitating rigorous conservation efforts. Traditional preservation techniques that have been developed over centuries involve surface treatment, structural stabilization, and gel-based cleaning to maintain both the integrity and aesthetic appeal of these artworks. Recent advances in artificial intelligence (AI)-powered predictive maintenance techniques offer innovative solutions to predict and prevent deterioration. By integrating image analysis and environmental monitoring, AI-based models provide valuable insights into painting preservation. This review comprehensively analyzes traditional and AI-based techniques for oil painting maintenance, highlighting the importance of adopting innovative approaches. By integrating traditional expertise with AI technology, conservators can enhance their capacity to maintain and preserve these cultural treasures for future generations.

With the great flexibility and performance of deep learning technology, there have been many attempts to replace existing functions inside video codecs such as High-Efficiency Video Coding (HEVC) with deep-learning-based solutions. One of the most researched approaches is adopting a deep network as an image restoration filter to recover distorted compressed frames. In this paper, instead, we introduce a novel idea for using a deep network, in which it chooses and transmits the side information according to the type of errors and contents, inspired by the sample adaptive offset filter in HEVC. A part of the network computes the optimal offset values while another part estimates the type of error and contents simultaneously. The combination of two subnetworks can address the estimation of highly nonlinear and complicated errors compared to conventional deep-learning-based schemes. Experimental results show that the proposed system yields an average bit-rate saving of 4.2% and 2.8% for the low-delay P and random access modes, respectively, compared to the conventional HEVC. Moreover, the performance improvement is up to 6.3% and 3.9% for higher-resolution sequences.

Depth maps play an important role in the representation of 3D information. They are often simultaneously acquired with color images; however, their resolution is significantly lower than that of color images owing to hardware limitations. In this paper, we propose a novel approach to upsample depth maps by using geometric deformation instead of pixel value refinement, which is employed in a majority of existing methods. This approach, known as grid warping, displaces the position of blurred pixels around the edge towards the center of the edge. The displacement vector for warping is obtained from an analysis of the corresponding high-resolution color image. Furthermore, we propose an edge signal and displacement vector modeling for a more effective analysis. The experimental results show that the proposed method significantly improves the quantitative and visual performance, as compared to state-of-the-art methods. The source codes of the proposed method will be available at https://github.com/yym064/DeepGridWarp.