Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model

TL;DR

This paper introduces the first large-scale database and evaluation model for assessing the quality of text-to-3D assets, addressing the lack of standardized quality assessment methods in this emerging field.

Contribution

It creates the largest text-to-3D asset quality assessment database and develops a benchmark and model for evaluating 3D assets from multiple subjective and objective perspectives.

Findings

Established the AIGC-T23DAQA database with 969 assets

Developed a comprehensive benchmark for T23DA quality assessment

Proposed an effective model for evaluating 3D assets from multiple perspectives

Abstract

Recent advancements in text-to-image (T2I) generation have spurred the development of text-to-3D asset (T23DA) generation, leveraging pretrained 2D text-to-image diffusion models for text-to-3D asset synthesis. Despite the growing popularity of text-to-3D asset generation, its evaluation has not been well considered and studied. However, given the significant quality discrepancies among various text-to-3D assets, there is a pressing need for quality assessment models aligned with human subjective judgments. To tackle this challenge, we conduct a comprehensive study to explore the T23DA quality assessment (T23DAQA) problem in this work from both subjective and objective perspectives. Given the absence of corresponding databases, we first establish the largest text-to-3D asset quality assessment database to date, termed the AIGC-T23DAQA database. This database encompasses 969 validated 3D assets generated from 170 prompts via 6 popular text-to-3D asset generation models, and corresponding subjective quality ratings for these assets from the perspectives of quality, authenticity, and text-asset correspondence, respectively. Subsequently, we establish a comprehensive benchmark based on the AIGC-T23DAQA database, and devise an effective T23DAQA model to evaluate the generated 3D assets from the aforementioned three perspectives, respectively.