Text-to-3D generation has achieved remarkable progress in recent years, yet evaluating these methods remains challenging for two reasons: i) Existing benchmarks lack fine-grained evaluation on different prompt categories and evaluation dimensions. ii) Previous evaluation metrics only focus on a single aspect (e.g., text-3D alignment) and fail to perform multi-dimensional quality assessment. To address these problems, we first propose a comprehensive benchmark named MATE-3D. The benchmark contains eight well-designed prompt categories that cover single and multiple object generation, resulting in 1,280 generated textured meshes. We have conducted a large-scale subjective experiment from four different evaluation dimensions and collected 107,520 annotations, followed by detailed analyses of the results. Based on MATE-3D, we propose a novel quality evaluator named HyperScore. Utilizing hypernetwork to generate specified mapping functions for each evaluation dimension, our metric can effectively perform multi-dimensional quality assessment. HyperScore presents superior performance over existing metrics on MATE-3D, making it a promising metric for assessing and improving text-to-3D generation. The project is available at https://mate-3d.github.io/.

In recent years, static meshes with texture maps have become one of the most prevalent digital representations of 3D shapes in various applications, such as animation, gaming, medical imaging, and cultural heritage applications. However, little research has been done on the quality assessment of textured meshes, which hinders the development of quality-oriented applications, such as mesh compression and enhancement. In this paper, we create a large-scale textured mesh quality assessment database, namely SJTU-TMQA, which includes 21 reference meshes and 945 distorted samples. The meshes are rendered into processed video sequences and then conduct subjective experiments to obtain mean opinion scores (MOS). The diversity of content and accuracy of MOS has been shown to validate its heterogeneity and reliability. The impact of various types of distortion on human perception is demonstrated. 13 state-of-the-art objective metrics are evaluated on SJTU-TMQA. The results report the highest correlation is around 0.6, indicating the need for more effective objective metrics. The SJTU-TMQA is available at https://ccccby.github.io

To address the mesh quality assessment (MQA) problem, GeodesicP-SIM was proposed by jointly considering geometry and color features, demonstrating compelling performance in multiple benchmarks.However, GeodesicPSIM does not consider the multi-scale characteristics of human perception.To better mimic human subjective perception, we proposed a multi-scale MQA model called multi-scale Geodesic Patch Similarity (MS-GeodesicPSIM).Firstly, inspired by the multi-scale processing methods used in image and point cloud analysis, we propose a novel multi-scale representation of textured meshes based on mesh simplification techniques.Secondly, we extend GeodesicPSIM into a multi-scale version leveraging the proposed multi-scale representation.Specifically, we construct a multi-scale representation for the reference and distorted meshes, followed by fusing the results of GeodesicPSIM at different scales to obtain an overall quality score.Experimental results demonstrate the superior performance of the proposed MS-GeodesicPSIM compared to the single-scale GeodesicPSIM and other MQA metrics on three large and independent databases.Ablation studies further confirm that MS-GeodesicPSIM is robust to different model hyperparameter settings.The code for MS-GeodesicPSIM is available at https://github.com/ccccby/MS-GeodesicPSIM