ProjFormer：基于几何投影Transformer与跨模态语义约束的点云补全
ProjFormer: Point Cloud Completion via Geometric-Projective Transformer and Cross-Modal Semantic Constraints
浏览论文内容
中文总结 AI 辅助
针对现有点云补全方法几何一致性与适应性不足的问题，提出ProjFormer跨模态框架，通过投影引导视图注意力模块与几何感知路由网络实现高效特征聚合与融合，在轻量级设计下取得了具竞争力的补全性能。
中文摘要 AI 辅助
点云补全因局部观测存在严重稀疏性与歧义性，本质上是不适定问题。现有多视图方法通过融入2D语义缓解该问题，但常依赖学习得到的注意力机制与固定融合方式，缺乏几何一致性与适应性。我们提出ProjFormer，这是一个跨模态框架，通过显式投影与自适应特征路由实现几何一致的2D-3D交互。其中，投影引导视图注意力模块通过确定性投影将3D点与多视图特征对齐，实现高效且几何一致的特征聚合；在此基础上，几何感知路由网络对结构特征与观测驱动特征进行逐点自适应融合，以实现渐进式优化。实验表明，在轻量级设计下，ProjFormer兼具竞争力性能与提升的结构完整性。
英文摘要
Point cloud completion is inherently ill-posed due to severe sparsity and ambiguity in partial observations. Existing multi-view methods alleviate this by incorporating 2D semantics, but often rely on learned attention and fixed fusion, which lack geometric consistency and adaptability. We propose ProjFormer, a cross-modal framework that enforces geometry-consistent 2D-3D interaction through explicit projection and adaptive feature routing. A Projective Guided View Attention module aligns 3D points with multi-view features via deterministic projection, enabling efficient and geometrically consistent aggregation. Building on this, a geometry-aware routing network performs point-wise adaptive fusion of structural and observation-driven features for progressive refinement. Experiments show that, under a lightweight design, ProjFormer delivers competitive performance with improved structural completeness.
发表机构
- Hunan University（湖南大学）
机构由 AI 辅助整理，请以论文原文为准。
