Research

Paper

AI LLM March 23, 2026

Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

Authors

Xingyu Zhu, Liang Yi, Shuo Wang, Wenbo Zhu, Yonglinag Wu, Beier Zhu, Hanwang Zhang

Abstract

Multimodal 3D vision-language models show strong generalization across diverse 3D tasks, but their performance still degrades notably under domain shifts. This has motivated recent studies on test-time adaptation (TTA), which enables models to adapt online using test-time data. Among existing TTA methods, cache-based mechanisms are widely adopted for leveraging previously observed samples in online prediction refinement. However, they store only limited historical information, leading to progressive information loss as the test stream evolves. In addition, their prediction logits are fused heuristically, making adaptation unstable. To address these limitations, we propose BayesMM, a Multimodal Bayesian Distribution Learning framework for test-time point cloud analysis. BayesMM models textual priors and streaming visual features of each class as Gaussian distributions: textual parameters are derived from semantic prompts, while visual parameters are updated online with arriving samples. The two modalities are fused via Bayesian model averaging, which automatically adjusts their contributions based on posterior evidence, yielding a unified prediction that adapts continually to evolving test-time data without training. Extensive experiments on multiple point cloud benchmarks demonstrate that BayesMM maintains robustness under distributional shifts, yielding over 4% average improvement.

Metadata

arXiv ID: 2603.22070
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-23
Fetched: 2026-03-24 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.22070v1</id>\n    <title>Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning</title>\n    <updated>2026-03-23T15:03:47Z</updated>\n    <link href='https://arxiv.org/abs/2603.22070v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.22070v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Multimodal 3D vision-language models show strong generalization across diverse 3D tasks, but their performance still degrades notably under domain shifts. This has motivated recent studies on test-time adaptation (TTA), which enables models to adapt online using test-time data. Among existing TTA methods, cache-based mechanisms are widely adopted for leveraging previously observed samples in online prediction refinement. However, they store only limited historical information, leading to progressive information loss as the test stream evolves. In addition, their prediction logits are fused heuristically, making adaptation unstable. To address these limitations, we propose BayesMM, a Multimodal Bayesian Distribution Learning framework for test-time point cloud analysis. BayesMM models textual priors and streaming visual features of each class as Gaussian distributions: textual parameters are derived from semantic prompts, while visual parameters are updated online with arriving samples. The two modalities are fused via Bayesian model averaging, which automatically adjusts their contributions based on posterior evidence, yielding a unified prediction that adapts continually to evolving test-time data without training. Extensive experiments on multiple point cloud benchmarks demonstrate that BayesMM maintains robustness under distributional shifts, yielding over 4% average improvement.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-23T15:03:47Z</published>\n    <arxiv:comment>CVPR 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Xingyu Zhu</name>\n    </author>\n    <author>\n      <name>Liang Yi</name>\n    </author>\n    <author>\n      <name>Shuo Wang</name>\n    </author>\n    <author>\n      <name>Wenbo Zhu</name>\n    </author>\n    <author>\n      <name>Yonglinag Wu</name>\n    </author>\n    <author>\n      <name>Beier Zhu</name>\n    </author>\n    <author>\n      <name>Hanwang Zhang</name>\n    </author>\n  </entry>"
}