Test-time Adaptation for Point Cloud Denoising under Unseen Noise
Authors: Kun Jiang, Shida Fu, Fanhao Yi, Weiqing Li, Zhiyong Su
Organizations: School of Automation, Nanjing University of Science and Technology, Nanjing, Jiangsu Province, 210094, P.R. China · School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu Province, 210094, P.R. China
Although deep learning-based point cloud denoising methods have demonstrated impressive results in recent years, their effectiveness usually degrades substantially in real-world scenarios where the noise distribution of test point clouds deviates from that of the training set. To address this challenge, we propose a test-time adaptive denoising (TTAD) framework that enables existing denoising approaches to adapt to unknown noise patterns at test time without relying on additional supervision or retraining from source data. Taking a pre-trained denoising model and a test noisy point cloud as input, TTAD first employs a residual-driven noise modeling (RDNM) module to estimate the sample-specific noise distribution through analyzing the deviation between the noisy input and its pseudo-clean version denoised by the initial model. Then, a noise-aware contrastive adaptation (NACA) module is designed to build sample-specific noisy-noisier test-time training pair from the denoised point cloud, and update the model parameters over a few adaptation steps per sample at test time through contrastive learning. Furthermore, TTAD naturally extends to a continual TTAD (CTTAD) setting, facilitating efficient progressive refinement across sequential test samples with consistent noise distributions, while reducing the computational cost per sample. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach significantly improves the generalization ability of existing denoising models under unseen noise, achieving superior performance across multiple evaluation metrics.
Figures & tables
Figure 1: Illustration of existing point cloud denoising methods and the proposed test-time adaptive denoising (TTAD) framework. The source model (PointFilter [ 40 ] ) fθ is trained on synthetic datasets with Gaussian noise. fθ performs well on noisy point clouds with seen (Gaussian) noise (a), but fails under unseen noise (b). The proposed TTAD framework significantly enhances the denoising performance of fθ by adapting it to unseen noise distributions during test time (c).
Figure 2: Overview of the proposed TTAD framework. (a) The input noisy point cloud Xt is first denoised by a pre-trained model fθ to produce a pseudo-clean output Y~ . (b) The residual-driven noise modeling (RDNM) module utilizes the residual noise N^t=Xt−Y~ to estimate the test-time noise distribution p(n) of Xt via a lightweight Gaussian mixture model (GMM). (c) The noise-aware contrastive adaptation (NACA) module generates a sample-specific noisy-noisier pair (X~t(1),X~t(2)) of Y~ . Within each test-time adaptation step, we first use the reconstruction loss Lrecon , identity loss Lid , and consistency loss Lconsist to update the online model fθonline via gradient descent at each iteration step. After that, the target model’s parameters θtarget are updated as an exponential moving average (EMA) of the online model’s parameters θonline . Finally, we can use the final θtarget to obtain the adapted denoised result Yc=fθtarget(Xt) .
Method
1% Gaussian/Gaussian
2% Gaussian/Gaussian
CD ↓
P2M ↓
CD ↓
P2M ↓
Score
0.86
0.55
2.10
1.68
+ TTAD
0.90
0.58
1.66
1.26
+ CTTAD
0.89
0.57
1.74
1.28
PF
0.80
0.42
1.49
1.07
+ TTAD
0.82
0.44
1.27
0.91
Table 1: Performance comparison of denoising methods on the PUNet dataset under in-distribution Gaussian noise. “Train/Test” denotes the noise type used for training and testing, respectively. Bold and underlined values indicate the best and second-best performance, respectively. CD and P2M values are multiplied by 104 .
Method
1%
2%
Gaussian/Pulse
Gaussian/Exponential
Gaussian/Laplace
Gaussian/Uniform
Gaussian/Pulse
Gaussian/Exponential
Gaussian/Laplace
Gaussian/Uniform
CD ↓
P2M ↓
CD ↓
P2M ↓
CD ↓
P2M ↓
CD ↓
P2M ↓
CD ↓
P2M ↓
CD ↓
P2M ↓
CD ↓
P2M ↓
CD ↓
P2M ↓
Score
1.49
1.13
2.80
2.03
0.96
0.60
1.98
1.33
4.60
4.40
7.71
6.67
2.23
1.79
10.45
9.31
+ TTAD
1.10
0.74
2.55
1.90
0.95
0.62
1.32
0.86
3.72
3.50
6.20
5.62
1.46
1.10
8.15
6.66
+ CTTAD
1.12
0.77
2.37
1.77
0.95
0.62
1.33
0.89
3.66
3.52
5.64
5.17
1.53
1.12
7.41
6.13
PF
1.12
0.80
2.40
1.84
1.06
0.65
1.49
0.93
3.42
3.26
6.15
4.99
2.44
2.06
5.03
4.33
Table 2: Performance comparison of denoising methods on the PUNet dataset under unseen synthetic noise. “Train/Test” denotes the noise type used for training and testing, respectively. Bold and underlined values indicate the best and second-best performance, respectively. CD and P2M values are multiplied by 104 .
Method
1% Gaussian/Mixed
2% Gaussian/Mixed
CD ↓
P2M ↓
CD ↓
P2M ↓
Score
1.04
0.64
3.36
2.80
+ TTAD
0.99
0.63
1.84
1.40
+ CTTAD
0.97
0.63
1.80
1.36
PF
1.01
0.59
2.26
1.84
+ TTAD
1.03
0.62
2.03
1.34
Table 3: Performance comparison of denoising methods on the PUNet dataset under mixed unseen noise. “Train/Test” denotes the noise type used for training and testing, respectively. Bold and underlined values indicate the best and second-best performance, respectively. CD and P2M values are multiplied by 104 .
Figure 3: Visualization of denoising results on different unseen 2% noise conditions. All baseline models (Score [ 20 ] , PF [ 40 ] , IPFN [ 8 ] , LaPDA [ 9 ] , and PD-LTS [ 22 ] ) are trained on Gaussian noise and tested on inputs corrupted by (a) Pulse noise and (b) Exponential noise.
Figure 4: Visualization of denoising results on additional unseen 2% noise conditions. All baseline models (Score [ 20 ] , PF [ 40 ] , IPFN [ 8 ] , LaPDA [ 9 ] , and PD-LTS [ 22 ] ) are trained on Gaussian noise and tested on inputs corrupted by (a) Laplace noise, (b) Uniform noise, and (c) Mixed noise.
Figure 5: Qualitative results on the Paris-Rue-Madame dataset [ 26 ] . TTAD improves denoising quality under real-world noise, removing scattered outliers, suppressing LiDAR scan-line artifacts, and restoring smooth and coherent surface structures.
Figure 6: Average processing time comparison. The baseline model (blue) has a constant low runtime. Standard TTAD (green) incurs a constant high cost due to per-sample re-initialization. In contrast, CTTAD (orange) becomes increasingly efficient by reusing and incrementally updating parameters across samples.
Figure 7: Performance comparison under unseen 2% Pulse noise, showing the average error tracked over a sequence of point clouds. While TTAD (green) shows stable, strong performance, CTTAD (orange) initially trades a minor performance dip for long-term gain, ultimately outperforming both baselines.
RDNM
NNP
2%Gaussian
2%Pulse
2%Exponential
CD
P2M
CD
P2M
CD
P2M
✗
✗
1.63
1.21
4.00
2.84
6.44
5.31
✗
✓
1.42
1.25
4.12
4.57
5.56
6.00
✓
✗
1.72
1.33
3.01
2.55
5.16
4.97
✓
✓
1.36
0.99
2.44
2.50
4.47
3.94
Table 4: Ablation study on components in TTAD. Results are averaged over three selected baseline denoising methods. "NNP" denotes the noisy-noisier pairing strategy. A checkmark (✓) indicates the module is enabled, and a cross (✗) indicates it is disabled. CD and P2M values are multiplied by 104 . The best results under each noise type are highlighted in bold .
Figure 8: Visualization of noise direction distributions using spherical-to-polar projection. Left: Ground-truth input noise shows a structured pattern. Middle: Our RDNM captures the dominant directional structures effectively. Right: Standard Gaussian noise appears spatially uniform and lacks structure. Each dot represents a normalized noise direction projected to 2D; the denser areas indicate dominant noise directions.
Figure 9: Performance comparison of different parameter update strategies on point clouds under Gaussian and unseen (Pulse, Exponential) synthetic noise. Results are averaged over three selected baseline denoising methods. Each group compares three strategies: Baseline (blue), Fully Update (orange), and EMA (green), evaluated by Chamfer Distance (top row) and Point-to-Mesh Distance (bottom row). Across all noise types, the adaptation strategy with EMA consistently improves generalization to unseen noise while maintaining source-domain performance on Gaussian noise.
Figure 10: Effect of GMM component number M on the distribution fitting error (blue curve) and computational time (red curve) under complex mixed noise.
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
Inseok Kong, Geunyoung Jung, Jiyoung Jung
Department of Geo Informatics, University of Seoul · Department of Artificial Intelligence, University of Seoul
Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons. In this comprehensive survey, we formally define the CTTA problem, analyze the diverse continual domain shift patterns that characterize different evaluation protocols, and propose a hierarchical taxonomy that categorizes existing methods into three families: optimization-based strategies (entropy minimization, pseudo-labeling, parameter restoration), parameter-efficient methods (normalization layer adaptation, adaptive parameter selection), and architecture-based approaches (teacher-student frameworks, adapters, visual prompting, masked modeling). We systematically review representative methods within each category and present comparative benchmarks and experimental results across standard evaluation settings. Finally, we discuss the limitations of current approaches and highlight emerging research directions, including the adaptation of foundation models and black-box systems, thereby providing a roadmap for future research in robust continual test-time adaptation.
The University of Texas at Dallas, USA · LIVIA ETS Montreal, ILLS International Laboratory on Learning Systems (ILLS), McGill - ÉTS - MILA - CNRS - Université Paris-Saclay - CentraleSupélec · Tulane University, USA +2
Noisy and corrupted points can substantially degrade point cloud recognition performance, especially under challenging corruption settings. In particular, full fine-tuning of 3D pre-trained models may amplify the influence of outliers and overwrite robustness priors learned during pre-training, while naive parameter-efficient adaptation remains sensitive to corrupted tokens. To address this issue, we propose PSFT, a point-selection fine-tuning framework that improves robustness while remaining parameter-efficient. PSFT first estimates point-wise influence from pre-pooling features and adaptively retains minimally influential points to suppress outliers. Based on the selected subset, a prompt generation branch predicts layer-wise prompt tokens and injects them into a frozen backbone for lightweight downstream adaptation. To further mitigate residual noise after selection, we append a lightweight feature filter with bottleneck MLP transformation and Beta-gated residual blending to refine patch-token representations before prediction. Extensive experiments show that PSFT consistently reduces corruption error on ModelNet-C and ModelNet40-C across all tested 3D pre-trained backbones, while achieving the strongest ScanObjectNN-C results with ULIP-2 and Uni3D-B among the evaluated tuning strategies. Our implementation can be found at https://github.com/CVChMA/PSFT/tree/master.
Da Li, Chang Ma, Dongfu Yin
Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen), Shenzhen, China · Shenzhen University, Shenzhen, China