Textured mesh Quality Assessment using Geometry and Color Field Similarity

2025-05-16

AI Summary

Existing texture mesh quality assessment (TMQA) methods suffer from low accuracy, poor robustness, and high computational cost. To address these limitations, this paper proposes FMQM—a point-cloud-based quality assessment method leveraging geometric and color field similarity. Our key contributions are: (1) the first introduction of the Nearest Surface Point Color Field (NSPCF), which explicitly models texture distribution in 3D space; (2) a novel four-dimensional perceptual similarity metric jointly incorporating Signed Distance Fields (SDF), NSPCF, and their spatial gradients; and (3) simultaneous achievement of high accuracy, strong robustness, and low computational complexity. Extensive experiments on three standard benchmarks demonstrate that FMQM consistently outperforms all state-of-the-art TMQA metrics in both quality correlation and inference speed. The implementation is publicly available.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

Textured mesh quality assessment (TMQA) is critical for various 3D mesh applications. However, existing TMQA methods often struggle to provide accurate and robust evaluations. Motivated by the effectiveness of fields in representing both 3D geometry and color information, we propose a novel point-based TMQA method called field mesh quality metric (FMQM). FMQM utilizes signed distance fields and a newly proposed color field named nearest surface point color field to realize effective mesh feature description. Four features related to visual perception are extracted from the geometry and color fields: geometry similarity, geometry gradient similarity, space color distribution similarity, and space color gradient similarity. Experimental results on three benchmark datasets demonstrate that FMQM outperforms state-of-the-art (SOTA) TMQA metrics. Furthermore, FMQM exhibits low computational complexity, making it a practical and efficient solution for real-world applications in 3D graphics and visualization. Our code is publicly available at: https://github.com/yyyykf/FMQM.

Problem

• Accurate textured mesh quality assessment is challenging
• Existing methods lack robust geometry and color evaluation
• Proposing FMQM for efficient 3D mesh quality analysis

Innovation

• Uses signed distance fields for geometry
• Introduces nearest surface point color field
• Extracts four visual perception features