Metraipolis › archive › dc_7ec210e1883e
PCQA-R1: Advancing Generalized 3D Point Cloud Quality Assessment with Reinforcement Learning — arXiv:2608.18627
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18627
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:06:21.965Z
- SHA-256 of the archived text
6f3c41f2fb0924c994348b41729b703dab72827e7c1400680374782a5468f6ce- Stable URL of this page
https://metraipolis.com/documento/dc_7ec210e1883e
How to cite
PCQA-R1: Advancing Generalized 3D Point Cloud Quality Assessment with Reinforcement Learning — arXiv:2608.18627 — arXiv (en), https://arxiv.org/abs/2608.18627 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ec210e1883e (Metraipolis archive dc_7ec210e1883e, sha256 6f3c41f2fb0924c994348b41729b703dab72827e7c1400680374782a5468f6ce)
BibTeX
@misc{dc7ec210e1883e,
title = {PCQA-R1: Advancing Generalized 3D Point Cloud Quality Assessment with Reinforcement Learning — arXiv:2608.18627},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18627},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ec210e1883e; sha256 6f3c41f2fb0924c994348b41729b703dab72827e7c1400680374782a5468f6ce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18627. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
No-reference point cloud quality assessment (PCQA) has been an active topic in recent years and is used to measure and optimize the visual experience of point clouds. However, large multimodal models (LMMs) have rarely been explored in this area. Previous LMM-based methods mainly rely on supervised fine-tuning to directly predict numerical quality scores, lacking the ability to generalize across datasets with heterogeneous MOS scales and limited annotations. A key difficulty is that absolute MOS regression can be brittle across datasets with different score scales and distortion distributions, whereas relative quality ranking is more stable under such shifts. In this paper, we present PCQA-R1, the first reinforcement learning LMM for 3D point cloud quality assessment to simultaneously model quality understanding and scoring. Built upon the group relative policy optimization (GRPO) strategy, PCQA-R1 first constructs a chain-of-thought dataset, PCQA-CoT, which serves as cold-start training data through a reverse reasoning strategy that teaches the LMM to generate its reasoning process. We further introduce a Gaussian proximity reward that prevents calibration drift by anchoring score predictions to the source MOS range. Experimental results demonstrate that PCQA-R1 achieves state-of-the-art cross-dataset generalization across five benchmarks and competitive in-domain accuracy. Ablation studies support the role of ranking, Gaussian reward, and cold-start traces. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.18627 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T14:00:22.565Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).