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.
| Comments: | To be published in The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.25127 [cs.CV] |
| (or arXiv:2605.25127v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.25127 arXiv-issued DOI via DataCite (pending registration) |
From: Haoqing Wu [view email]
[v1]
Sun, 24 May 2026 15:15:13 UTC (1,715 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。