Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

TL;DR

This paper introduces BayesMM, a Bayesian framework for test-time point cloud analysis that models multimodal data as Gaussian distributions, improving robustness under domain shifts without additional training.

Contribution

BayesMM is the first to model multimodal point cloud data with Bayesian distribution learning for online adaptation, addressing cache-based limitations and fusion instability.

Findings

Achieves over 4% average improvement on point cloud benchmarks.

Maintains robustness under distributional shifts.

Automatically adjusts modality contributions via Bayesian model averaging.

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.