SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation

TL;DR

This paper introduces SRAM, a novel no-reference 3D shape realism evaluation metric that uses language models and a new dataset to better align with human perception of shape realism.

Contribution

We propose SRAM, a shape-realism alignment metric utilizing language models and a new dataset, enabling realistic 3D shape evaluation without ground truth references.

Findings

SRAM correlates well with human perception.

Outperforms existing 3D shape evaluation methods.

Demonstrates strong generalizability across different objects.

Abstract

3D generation and reconstruction techniques have been widely used in computer games, film, and other content creation areas. As the application grows, there is a growing demand for 3D shapes that look truly realistic. Traditional evaluation methods rely on a ground truth to measure mesh fidelity. However, in many practical cases, a shape's realism does not depend on having a ground truth reference. In this work, we propose a Shape-Realism Alignment Metric that leverages a large language model (LLM) as a bridge between mesh shape information and realism evaluation. To achieve this, we adopt a mesh encoding approach that converts 3D shapes into the language token space. A dedicated realism decoder is designed to align the language model's output with human perception of realism. Additionally, we introduce a new dataset, RealismGrading, which provides human-annotated realism scores without the need for ground truth shapes. Our dataset includes shapes generated by 16 different algorithms on over a dozen objects, making it more representative of practical 3D shape distributions. We validate our metric's performance and generalizability through k-fold cross-validation across different objects. Experimental results show that our metric correlates well with human perceptions and outperforms existing methods, and has good generalizability.