# MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds Source: [MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds]() Collection index: [llms.txt]() Data updated: 2026-06-13T05:00:05.486Z Authors: Inseok Kong, Geunyoung Jung, Jiyoung Jung Published: 2026-06-11T06:03:59.000Z ## Abstract 3D point cloud models suffer significant performance degradation under distribution shifts caused by sensor noise, occlusions, and environmental changes. Test-time adaptation (TTA) has emerged as a practical paradigm for mitigating this issue during inference. Recently, leveraging multi-view augmentation has shown promise in improving 3D TTA performance. However, existing multi-view approaches are often constrained by sequential optimization that treats each view independently. This sequential optimization leads to substantial inference latency due to repetitive optimization steps, making real-time adaptation impractical. To address this, we propose Masked Multi-View Test-Time Adaptation (MAMVI), which replaces sequential optimization with a unified single-step adaptation. Specifically, MAMVI utilizes a hybrid masking strategy that combines fixed ratios for stability with Beta-distributed sampling for diversity. By aggregating losses across multiple views, MAMVI performs adaptation through a single backward pass based on multi-view consensus. Additionally, a confidence-based adaptive learning rate is used to dynamically adjust the adaptation intensity for each sample. Extensive experiments on ModelNet-40C, ShapeNet-C, and ScanObjectNN-C demonstrate that MAMVI achieves state-of-the-art accuracy on ShapeNet-C and ScanObjectNN-C. Moreover, it remains competitive on ModelNet-40C while delivering 4.9-8.9 times faster inference, making it highly suitable for real-time applications. Our code is available at https://github.com/Inseok-kong/MAMVI ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [3D Point Cloud Classification on ShapeNet-C](): 3D Point Cloud Classification; ShapeNet-C; Accuracy (Uniform Noise): 81.7. - [3D Point Cloud Classification on ScanObjectNN-C 1.0 (test)](): 3D Point Cloud Classification; ScanObjectNN-C 1.0 (test); Accuracy (Uniform Noise): 43.06. - [3D Point Cloud Classification on ModelNet40-C (test)](): 3D Point Cloud Classification; ModelNet40-C (test); Robustness to Rotation: 66.27. ## Original sources and implementation [Original paper]() [PDF]()