{"slug": "mage-view-guided-point-cloud-completion-with-efficient-modality-alignment-and", "title": "MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement", "summary": "Researchers propose MAGE, a geometry-aware framework for view-guided point cloud completion that integrates efficient modality alignment and adaptive geometry enhancement to address cross-modal geometric inconsistency. The method achieves superior performance on synthetic and real-world datasets compared to existing approaches.", "body_md": "arXiv:2607.02568v1 Announce Type: new\nAbstract: View-based point cloud completion aims to recover a complete 3D shape from a partial point cloud, guided by a single-view image. However, existing approaches often suffer from limited performance due to weak modality alignment and limited self-geometry enhancement. To overcome these challenges, we propose a unified geometry-aware framework that integrates efficient modality alignment and adaptive geometry enhancement, mainly to address cross-modal geometric inconsistency of view-guided point cloud completion. Specifically, we propose a geometry-aware modality alignment by integrating a shared self-attention Transformer and cross-modality reconstruction supervision, which aims to bring features of the image and point cloud close to each other in a shared latent space describing the 3D object. To enhance the perception of global shape and local geometric details, we propose an adaptive geometry-aware self-attention module, which simultaneously considers local geometry-aware attention computation and the spatially-variant feature fusion. In addition, we apply a geometry-perceptive anchor refinement module to reorganize the anchor points (representing a local region of the shape) under appropriate supervision, further boosting the completion performance of our method. Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves superior performance over existing approaches. Our code will be available at https://github.com/weizequan/MAGE.", "url": "https://wpnews.pro/news/mage-view-guided-point-cloud-completion-with-efficient-modality-alignment-and", "canonical_source": "https://arxiv.org/abs/2607.02568", "published_at": "2026-07-07 04:00:00+00:00", "updated_at": "2026-07-07 04:07:49.193365+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "neural-networks"], "entities": ["MAGE", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/mage-view-guided-point-cloud-completion-with-efficient-modality-alignment-and", "markdown": "https://wpnews.pro/news/mage-view-guided-point-cloud-completion-with-efficient-modality-alignment-and.md", "text": "https://wpnews.pro/news/mage-view-guided-point-cloud-completion-with-efficient-modality-alignment-and.txt", "jsonld": "https://wpnews.pro/news/mage-view-guided-point-cloud-completion-with-efficient-modality-alignment-and.jsonld"}}