Color reconstruction of ancient paintings based on dual pooling attention and pixel adaptive convolution

In order to address inaccurate colors in reconstructed results, inconsistent color reconstruction for background and content, and poor local color reconstruction, a model is proposed for the color reconstruction of ancient paintings based on dual pooling attention and pixel adaptive convolution. Firstly, a Dual Pooling Channel Attention module is proposed to address inaccurate colors in reconstructed results. This module enhances the model’s ability to extract features by assigning different weights to the image channels, thereby reducing inaccurate colors. Additionally, to solve the problem of inconsistent color reconstruction due to variations in background and content, a Content Adaptive Feature Extraction module is constructed. This module adaptively adjusts the convolutional parameters in terms of the differences in background and content, improving the overall effectiveness of color reconstruction. Lastly, a Contrastive Coherence Preserving Loss is introduced to solve the problem of poor reconstruction of local colors. The loss enhances the model’s focus on image localization by constraining local features, thereby improving the local color reconstruction. Comparison experiments and ablation experiments are performed on various datasets. Experimental results show that, compared with the latest models, the proposed model effectively preserves the structural information and content details of ancient paintings. It produces reconstructed results with clear outlines and harmonious colors, achieving better color reconstructed results both globally and locally.