PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration

• URL: http://arxiv.org/abs/2605.25127v1
• Date: Sun, 24 May 2026 15:15:13 GMT
• Title: PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration
• Abstract summary: Real-world point clouds often suffer from degradations such as incompleteness, noise, outliers, and irregular density.<n>We propose a unified 3D restoration network that directly takes point clouds as input and adaptively reconstructs high-quality geometry under diverse degradation scenarios.
• Score: 2.6189995284654737
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point clouds are a fundamental 3D representation in computer vision, enabling a wide range of perception tasks. However, real-world point clouds often suffer from degradations such as incompleteness, noise, outliers, and irregular density, caused by sensor limitations or occlusions. Recovering clean and detailed shapes from such degraded data is crucial for downstream applications. While existing learning-based methods achieve progress on individual tasks like completion or denoising, they typically rely on global bottleneck features, which lose fine-grained geometry and remain sensitive to varying input quality. We propose a unified 3D restoration network that directly takes point clouds as input and adaptively reconstructs high-quality geometry under diverse degradation scenarios. At the core of our approach is a Pseudo-Query module, implemented within a Transformer backbone, which reformulates geometric translation into two cooperative stages to enhance structural clarity, robustness, and local detail preservation. Extensive experiments on curated benchmarks demonstrate that our approach surpasses state-of-the-art performance in general 3D restoration. It effectively handles complex combinations of completion, deformation, and denoising degradations. With this work, we provide a novel unified, point-only backbone for robust 3D restoration, enabling more versatile 3D perception.

Related papers

• CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration [26.457061044468915]
  We propose CMHANet, a novel Cross-Modal Hybrid Attention Network.<n>Our method integrates the fusion of rich contextual information from 2D images with the geometric detail of 3D point clouds.<n>We show that our method achieves substantial improvements in both registration accuracy and overall robustness, outperforming current techniques.
  arXiv  Detail & Related papers  (2026-03-13T07:09:22Z)
• Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformer [52.40992954884257]
  3D visualization techniques have fundamentally transformed how we interact with digital content.<n>Massive data size of point clouds presents significant challenges in data compression.<n>We propose an end-to-end deep learning framework that seamlessly integrates PCAC with differentiable rendering.
  arXiv  Detail & Related papers  (2024-11-12T16:12:51Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• Deep Point Cloud Reconstruction [74.694733918351]
  Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. We propose a deep point cloud reconstruction network consisting of two stages: 1) a 3D sparse stacked-hourglass network as for the initial densification and denoising, 2) a refinement via transformers converting the discrete voxels into 3D points.
  arXiv  Detail & Related papers  (2021-11-23T07:53:28Z)
• PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers [81.71904691925428]
  We present a new method that reformulates point cloud completion as a set-to-set translation problem. We also design a new model, called PoinTr, that adopts a transformer encoder-decoder architecture for point cloud completion. Our method outperforms state-of-the-art methods by a large margin on both the new benchmarks and the existing ones.
  arXiv  Detail & Related papers  (2021-08-19T17:58:56Z)
• Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds [54.31515001741987]
  We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds. We achieve this by imposing a novel point discrimination loss on the middle level and global level point features. Our method learns powerful representations and achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-08-04T15:11:48Z)
• HyperPocket: Generative Point Cloud Completion [19.895219420937938]
  We introduce a novel autoencoder-based architecture called HyperPocket that disentangles latent representations. We leverage a hypernetwork paradigm to fill the spaces, dubbed pockets, that are left by the missing object parts. Our method offers competitive performances to the other state-of-the-art models.
  arXiv  Detail & Related papers  (2021-02-11T12:30:03Z)
• RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction [19.535169371240073]
  We introduce RfD-Net that jointly detects and reconstructs dense object surfaces directly from point clouds. We decouple the instance reconstruction into global object localization and local shape prediction. Our approach consistently outperforms the state-of-the-arts and improves over 11 of mesh IoU in object reconstruction.
  arXiv  Detail & Related papers  (2020-11-30T12:58:05Z)
• GRNet: Gridding Residual Network for Dense Point Cloud Completion [54.43648460932248]
  Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. We propose a novel Gridding Residual Network (GRNet) for point cloud completion. Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks.
  arXiv  Detail & Related papers  (2020-06-06T02:46:39Z)

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.