mlsanityData to 7 Oct 2026

Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

arXiv 2603.22070 ↗First posted 23 Mar 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 48 of its 54 references that are in the map. First posted on arXiv 23 Mar 2026.

Builds on

48 of 54 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Open-Vocabulary Point-Cloud Object Detection without 3D Annotation3 Apr
  2. 2021PointCLIP: Point Cloud Understanding by CLIP4 Dec

Other references · 46

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  3. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  4. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  5. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  6. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  7. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  8. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  9. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  10. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  11. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  12. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 231
34 more
  1. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 199
  2. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 199
  3. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  4. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  5. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  6. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 150
  7. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 149
  8. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  9. 2024Efficient Test-Time Adaptation of Vision-Language Modelscited by 138
  10. 2025On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectificationcited by 121
  11. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  12. 2025KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Modelscited by 69
  13. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  14. 2024Number it: Temporal Grounding Videos like Flipping Mangacited by 65
  15. 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptationcited by 51
  16. 2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Modelscited by 51
  17. 2024Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correctingcited by 26
  18. 2022MATE: Masked Autoencoders are Online 3D Test-Time Learnerscited by 23
  19. 2022MetaSets: Meta-Learning on Point Sets for Generalizable Representationscited by 22
  20. 2024DOTA: Distributional Test-Time Adaptation of Vision-Language Modelscited by 22
  21. 2025Bayesian Test-Time Adaptation for Vision-Language Modelscited by 21
  22. 2018A Simple Cache Model for Image Recognitioncited by 20
  23. 2024Backpropagation-free Network for 3D Test-time Adaptationcited by 14
  24. 2025Realistic Test-Time Adaptation of Vision-Language Modelscited by 14
  25. 2025Enhancing CLIP Robustness via Cross-Modality Alignmentcited by 14
  26. 2025Dynamic Multimodal Prototype Learning in Vision-Language Modelscited by 13
  27. 2024CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformationcited by 11
  28. 2024Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmarkcited by 9
  29. 2024Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysiscited by 6
  30. 2025Online Gaussian Test-Time Adaptation of Vision-Language Modelscited by 6
  31. 2025Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Modelscited by 6
  32. 2025Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignmentcited by 5
  33. 2025Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysiscited by 4
  34. 2025Revisiting Bayesian Model Averaging in the Era of Foundation Modelscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models
  2. 2025Point Cloud Quantization through Multimodal Prompting for 3D Understanding
  3. 2025Consistency Diffusion Models for Single-Image 3D Reconstruction with Priors
  4. 2024Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models
  5. 2025BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis
  6. 2025Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models
  7. 2026CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation
  8. 2026Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuning