Enhancing 3D Scene Representation with Structural Dissimilarity-Aware Learning

Novel view synthesis aims to generate high-quality unseen views from images at different viewpoints. However, existing methods often struggle to preserve fine details, leading to structural distortions in complex regions. In this paper, we introduce a simple yet effective structure-aware objective function designed to enhance structural information in novel view synthesis. By leveraging the Structural Similarity Index (SSIM), our method attends to regions exhibiting significant structural distortions. We incorporate structural dissimilarity-based attention to highlight discrepancies in challenging regions between predicted and ground-truth images. It enables recent 3D scene representation models to achieve improved structural preservation, leading to more coherent representations. Experiments on synthetic and real-world datasets demonstrate that our method enhances structural consistency, particularly in challenging regions.