🤖 AI Summary
Existing full-reference 3D mesh quality assessment (MQA) methods struggle to model the complex interplay between geometric structure and texture information, leading to significant discrepancies between predicted scores and human perceptual judgments. To address this, we propose the first hybrid MQA framework that synergistically integrates model-driven and projection-driven paradigms. Our key contributions are: (1) a geometry–texture interaction-aware assessment paradigm; (2) a differentiable rendering mechanism with feature alignment, enabling joint representation of 3D geometry and color textures; and (3) a cross-modal cross-attention module coupled with a multi-scale graph neural network for hierarchical feature fusion. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art approaches, achieving over 8% improvement in Spearman rank correlation coefficient (SRCC) and linear correlation coefficient (LCC) against subjective ratings. The source code will be made publicly available.
📝 Abstract
Mesh quality assessment (MQA) models play a critical role in the design, optimization, and evaluation of mesh operation systems in a wide variety of applications. Current MQA models, whether model-based methods using topology-aware features or projection-based approaches working on rendered 2D projections, often fail to capture the intricate interactions between texture and 3D geometry. We introduce HybridMQA, a first-of-its-kind hybrid full-reference colored MQA framework that integrates model-based and projection-based approaches, capturing complex interactions between textural information and 3D structures for enriched quality representations. Our method employs graph learning to extract detailed 3D representations, which are then projected to 2D using a novel feature rendering process that precisely aligns them with colored projections. This enables the exploration of geometry-texture interactions via cross-attention, producing comprehensive mesh quality representations. Extensive experiments demonstrate HybridMQA's superior performance across diverse datasets, highlighting its ability to effectively leverage geometry-texture interactions for a thorough understanding of mesh quality. Our implementation will be made publicly available.