PIT-QMM: A Large Multimodal Model for No-Reference Point Cloud Quality Assessment
Keywords: Multimedia quality assessment, point clouds, large multimodal models
Abstract: Large Multimodal Models (LMMs) have recently enabled considerable advances in the realm of image and video quality assessment, but this progress has yet to be translated to the domain of 3D assets. We are interested in using these models to conduct No-Reference Point Cloud Quality Assessment (NR-PCQA), where the aim is to automatically evaluate the perceptual quality of a point cloud in absence of a reference. We begin with the observation that different modalities of data -- text descriptions, 2D projections, and 3D point cloud views -- provide uniquely useful insights into point cloud quality. We leverage this to devise a multimodal dataset construction strategy providing a holistic combination of multiple types and levels of information. We then construct PIT-QMM, a novel LMM for NR-PCQA that is capable of consuming text, images and point clouds to predict quality scores. Extensive experimentation shows that our proposed method outperforms the state-of-the-art by significant margins on popular benchmarks with fewer training iterations, and thorough ablations validate our dataset construction strategy. Code and datasets are available at https://anonymous.4open.science/r/pit-qmm-BD1F/.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12632
Loading