The preservation of cultural heritage murals requires accurate damage prediction, a task hindered by the prohibitive cost of pixel-level annotations. To overcome this annotation bottleneck, we propose a framework that requires only inexpensive bounding-box supervision. Our approach first employs a background-attention-guided strategy to generate high-quality pseudo-labels for mural damage from these bounding-box inputs. These labels then train our Multi-scale Dual-branch Attention Network (MDANet), an architecture specifically designed to disentangle complex damage from intricate mural textures. For evaluation, we introduce the Yunnan Mural Bounding-box Dataset (YMBD), the first publicly available dataset for this task. Our method achieves a 62.1% Intersection over Union (IoU) on YMBD, establishing a strong benchmark for future research.

Abstract Image denoising aims to remove noise from images and improve the quality of images. However, most image denoising methods heavily rely on pairwise training strategies and strict prior knowledge about image structure or noise distribution. While these methods exhibit significant results when handling known types of noise, their generalization performance diminishes when confronted with images containing unknown noise distributions. To address this issue, a two‐stage approach is introduced for enhancing the generalizability of image denoising. The proposed method does not rely on a large amount of paired data or prior knowledge of the noise type and level. Instead, it constructs a denoising pipeline with improved generalizability through an MLP‐based denoiser and generative diffusion prior. Specifically, in the first stage, an initial denoised image is predicted with a structure resembling that of the underlying clean image by introducing an MLP‐based U‐shaped denoising network aided by an implicit structural prior. In the second stage, the generalizability and quality of the denoiser are further enhanced by conditioning the result obtained from the previous stage on the pretrained denoising diffusion null‐space model. Extensive experimentation on multiple datasets demonstrates that this method exhibits better denoising performance and generalizability than other image denoising methods.