LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM

TL;DR

This paper introduces a novel method that leverages large multi-modality models (LMMs) with text supervision to improve point cloud quality assessment, combining 2D projections and structural features for more accurate 3D visual quality evaluation.

Contribution

It presents the first integration of LMMs into PCQA by transforming quality labels into text and combining features for enhanced assessment accuracy.

Findings

LMMs can effectively assess point cloud quality with text supervision.

Combining textual and structural features improves evaluation accuracy.

The approach outperforms existing PCQA methods.

Abstract

Although large multi-modality models (LMMs) have seen extensive exploration and application in various quality assessment studies, their integration into Point Cloud Quality Assessment (PCQA) remains unexplored. Given LMMs' exceptional performance and robustness in low-level vision and quality assessment tasks, this study aims to investigate the feasibility of imparting PCQA knowledge to LMMs through text supervision. To achieve this, we transform quality labels into textual descriptions during the fine-tuning phase, enabling LMMs to derive quality rating logits from 2D projections of point clouds. To compensate for the loss of perception in the 3D domain, structural features are extracted as well. These quality logits and structural features are then combined and regressed into quality scores. Our experimental results affirm the effectiveness of our approach, showcasing a novel integration of LMMs into PCQA that enhances model understanding and assessment accuracy. We hope our contributions can inspire subsequent investigations into the fusion of LMMs with PCQA, fostering advancements in 3D visual quality analysis and beyond. The code is available at https://github.com/zzc-1998/LMM-PCQA.