📝 SummarXiv

Abstract

The automated prediction of facial beauty is a benchmark task in affective computing that requires a sophisticated understanding of both local aesthetic details (e.g., skin texture) and global facial harmony (e.g., symmetry, proportions). Existing models, based on either Convolutional Neural Networks (CNNs) or Vision Transformers (ViTs), exhibit inherent architectural biases that limit their performance; CNNs excel at local feature extraction but struggle with long-range dependencies, while ViTs model global relationships at a significant computational cost. This paper introduces the \textbf{Mamba-Diffusion Network (MD-Net)}, a novel dual-stream architecture that resolves this trade-off by delegating specialized roles to state-of-the-art models. The first stream leverages a frozen U-Net encoder from a pre-trained latent diffusion model, providing a powerful generative prior for fine-grained aesthetic qualities. The second stream employs a Vision Mamba (Vim), a modern state-space model, to efficiently capture global facial structure with linear-time complexity. By synergistically integrating these complementary representations through a cross-attention mechanism, MD-Net creates a holistic and nuanced feature space for prediction. Evaluated on the SCUT-FBP5500 benchmark, MD-Net sets a new state-of-the-art, achieving a Pearson Correlation of \textbf{0.9235} and demonstrating the significant potential of hybrid architectures that fuse generative and sequential modeling paradigms for complex visual assessment tasks.