UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising

• URL: http://arxiv.org/abs/2604.16976v1
• Date: Sat, 18 Apr 2026 12:09:29 GMT
• Title: UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising
• Abstract summary: Point cloud denoising is a fundamental and crucial challenge in real-world point cloud applications.<n>Existing quantitative evaluation metrics for point cloud denoising methods are implemented in a supervised manner.<n>We propose a simple yet effective unsupervised geometric distance (UGD) for real-world noisy point cloud denoising.
• Score: 13.787651683814133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud denoising is a fundamental and crucial challenge in real-world point cloud applications. Existing quantitative evaluation metrics for point cloud denoising methods are implemented in a supervised manner, which requires both the denoised point cloud and the corresponding ground-truth clean point cloud to compute a representative geometric distance. This requirement is highly problematic in real-world scenarios, where ground-truth clean point clouds are often unavailable. In this paper, we propose a simple yet effective unsupervised geometric distance (UGD) for real-world noisy point cloud denoising, calculated solely from noisy point clouds. The core idea of UGD is to learn a patch-wise prior model from a set of clean point clouds and then employ this prior model as the ground-truth to quantify the degradation by measuring the geometric variations of the denoised point cloud. To this end, we first learn a pristine Gaussian Mixture Model (GMM) with extracted patch-wise quality-aware features from a set of pristine clean point clouds by a patch-wise feature extraction network, which serves as the ground-truth for the quantitative evaluation. Then, the UGD is defined as the weighted sum of distances between each patch of the denoised point cloud and the learned pristine GMM model in the patch space. To train the employed patch-wise feature extraction network, we propose a self-supervised training framework through multi-task learning, which includes pair-wise quality ranking, distortion classification, and distortion distribution prediction. Quantitative experiments with synthetic noise confirm that the proposed UGD achieves comparable performance to supervised full-reference metrics. Moreover, experimental results on real-world data demonstrate that the proposed UGD enables unsupervised evaluation of point cloud denoising methods based exclusively on noisy point clouds.

Related papers

• U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching [87.76453413654922]
  We introduce U-CAN, an Unsupervised framework for point cloud denoising with Consistency-Aware Noise2Noise matching.<n>Specifically, we leverage a neural network to infer a multi-step denoising path for each point of a shape or scene with a noise to noise matching scheme.<n>We introduce a novel constraint on the denoised geometry consistency for learning consistency-aware denoising patterns.
  arXiv  Detail & Related papers  (2025-10-29T06:20:21Z)
• UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis [36.565699477170504]
  Existing methods focus on enhancing point cloud quality by developing dedicated denoising and completion models.<n>We propose a unified point-level prompting method that reformulates point cloud denoising and completion as a prompting mechanism.<n>Extensive experiments on four datasets demonstrate the superiority and robustness of our method when handling noisy and incomplete point cloud data.
  arXiv  Detail & Related papers  (2025-07-25T06:54:30Z)
• RBFIM: Perceptual Quality Assessment for Compressed Point Clouds Using Radial Basis Function Interpolation [58.04300937361664]
  One of the main challenges in point cloud compression (PCC) is how to evaluate the perceived distortion so that the RB can be optimized for perceptual quality.<n>We propose a novel assessment method, utilizing radial basis function (RBF) to convert discrete point features into a continuous feature function for the distorted point cloud.
  arXiv  Detail & Related papers  (2025-03-18T11:25:55Z)
• Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentation [15.881442863961531]
  We introduce a novel scheme for induced geometric invariance of point cloud representations across domains. On one hand, a novel pretext task of predicting translation of distances of augmented samples is proposed to alleviate centroid shift of point clouds. On the other hand, we pioneer an integration of the relational self-supervised learning on geometrically-augmented point clouds.
  arXiv  Detail & Related papers  (2024-09-11T02:39:19Z)
• Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling [55.05706827963042]
  Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud. Previous methods typically split a sparse point cloud into several local patches, upsample patch points, and merge all upsampled patches. We propose a novel approach that learns an unsigned distance field guided by local priors for point cloud upsampling.
  arXiv  Detail & Related papers  (2023-12-23T01:52:14Z)
• A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling [10.390581335119098]
  We propose a conditional denoising diffusion probability model (DDPM) for point cloud upsampling, called PUDM. PUDM treats the sparse point cloud as a condition, and iteratively learns the transformation relationship between the dense point cloud and the noise. PUDM exhibits strong noise robustness in experimental results.
  arXiv  Detail & Related papers  (2023-12-03T12:41:41Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration [24.275038551236907]
  We propose an effective inlier estimation method for unsupervised point cloud registration. We capture geometric structure consistency between the source point cloud and its corresponding reference point cloud copy. We train the proposed model in an unsupervised manner, and experiments on synthetic and real-world datasets illustrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2023-07-26T08:04:01Z)
• PointPatchMix: Point Cloud Mixing with Patch Scoring [58.58535918705736]
  We propose PointPatchMix, which mixes point clouds at the patch level and generates content-based targets for mixed point clouds. Our approach preserves local features at the patch level, while the patch scoring module assigns targets based on the content-based significance score from a pre-trained teacher model. With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86.3% accuracy on ScanObjectNN and 94.1% accuracy on ModelNet40.
  arXiv  Detail & Related papers  (2023-03-12T14:49:42Z)
• TCDM: Transformational Complexity Based Distortion Metric for Perceptual Point Cloud Quality Assessment [24.936061591860838]
  The goal of objective point cloud quality assessment (PCQA) research is to develop metrics that measure point cloud quality in a consistent manner. We evaluate the point cloud quality by measuring the complexity of transforming the distorted point cloud back to its reference. The effectiveness of the proposed transformational complexity based distortion metric (TCDM) is evaluated through extensive experiments conducted on five public point cloud quality assessment databases.
  arXiv  Detail & Related papers  (2022-10-10T13:20:51Z)
• PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition [111.55944556661626]
  We propose Point-Cloud Contrastive Adversarial Training (PointCAT) to boost the robustness of point cloud recognition models. We leverage a supervised contrastive loss to facilitate the alignment and uniformity of the hypersphere features extracted by the recognition model. To provide the more challenging corrupted point clouds, we adversarially train a noise generator along with the recognition model from the scratch.
  arXiv  Detail & Related papers  (2022-09-16T08:33:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.