Test-time Adaptation for Point Cloud Denoising under Unseen Noise

Kun Jiang; Shida Fu; Fanhao Yi; Weiqing Li; Zhiyong Su

cs.CVOct 20, 2026

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

Abstract

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 ] ) $f_{\theta}$ is trained on synthetic datasets with Gaussian noise. $f_{\theta}$ 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 $f_{\theta}$ 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 $X_{t}$ is first denoised by a pre-trained model $f_{\theta}$ to produce a pseudo-clean output $\tilde{Y}$ . (b) The residual-driven noise modeling (RDNM) module utilizes the residual noise $\hat{\mathcal{N}}_{t}=X_{t}-\tilde{Y}$ to estimate the test-time noise distribution $p(\mathbf{n})$ of $X_{t}$ via a lightweight Gaussian mixture model (GMM). (c) The noise-aware contrastive adaptation (NACA) module generates a sample-specific noisy-noisier pair $(\tilde{X}_{t}^{(1)},\tilde{X}_{t}^{(2)})$ of $\tilde{Y}$ . Within each test-time adaptation step, we first use the reconstruction loss $\mathcal{L}_{\text{recon}}$ , identity loss $\mathcal{L}_{\text{id}}$ , and consistency loss $\mathcal{L}_{\text{consist}}$ to update the online model $f_{\theta_{\text{online}}}$ via gradient descent at each iteration step. After that, the target model’s parameters $\theta_{\text{target}}$ are updated as an exponential moving average (EMA) of the online model’s parameters $\theta_{\text{online}}$ . Finally, we can use the final $\theta_{\text{target}}$ to obtain the adapted denoised result $Y_{c}=f_{\theta_{\text{target}}}(X_{t})$ .

Method	1% Gaussian/Gaussian		2% Gaussian/Gaussian
Method	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$
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

10^{4}

Method	1%								2%
Method	Gaussian/Pulse		Gaussian/Exponential		Gaussian/Laplace		Gaussian/Uniform		Gaussian/Pulse		Gaussian/Exponential		Gaussian/Laplace		Gaussian/Uniform
	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$
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

10^{4}

Method	1% Gaussian/Mixed		2% Gaussian/Mixed
Method	CD $\downarrow$	P2M $\downarrow$	CD $\downarrow$	P2M $\downarrow$
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

10^{4}

Panel of Figure 3 — 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.

Panel of Figure 4 — 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.

Panel of Figure 7 — 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
RDNM	NNP	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

10^{4}

. 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.

Point Cloud Denoising

See all 11 papers

MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds
Jun 11, 2026Inseok Kong, Geunyoung Jung, Jiyoung JungTest-Time Adaptation Point Cloud Classification
Department of Geo Informatics, University of Seoul · Department of Artificial Intelligence, University of Seoul
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
Jul 9, 2026Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang +6Source-Free Domain Adaptation Distribution Shift Robustness
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
Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification
Jul 22, 2026Da Li, Chang Ma, Dongfu YinPoint Cloud Classification Parameter-Efficient Fine-Tuning
Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen), Shenzhen, China · Shenzhen University, Shenzhen, China

Jun 11, 2026J/K move · Enter open · S save

MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds

Inseok Kong, Geunyoung Jung, Jiyoung Jung

Department of Geo Informatics, University of Seoul · Department of Artificial Intelligence, University of Seoul

Test-Time Adaptation Point Cloud Classification Point Cloud Learning Multi-View Learning

Open paper AskPDF arXiv

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

Abstract

Point Cloud Denoising

Explore similar work

MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds

Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification