GGPT：几何锚定的点 Transformer
GGPT: Geometry-Grounded Point Transformer
把 SfM 得到的稀疏点云作为显式几何监督，去精修前馈网络输出的稠密点图，这个「稀疏几何引导稠密预测」的范式可以直接迁移到 VGGT、DUSt3R 类模型的几何一致性提升上。
原文依据 a geometry-guided 3D point transformer that refines dense point maps under explicit partial-geometry supervision
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的前馈网络通过直接从 RGB 图像预测稠密点图，在稀疏视图三维重建上取得了显著进展。然而，由于缺乏显式的多视图约束，这类方法常常出现几何不一致以及细粒度精度有限的问题。我们提出几何锚定的点 Transformer（GGPT），一个用可靠稀疏几何引导来增强前馈重建的框架。我们首先提出一种改进的运动恢复结构流程，它基于稠密特征匹配与轻量几何优化，从稀疏输入视图中高效估计出准确的相机位姿与部分三维点云。我们提出一个几何引导的三维点 Transformer，借助优化后的引导编码，在显式的部分几何监督下精修稠密点图。大量实验表明，我们的方法为将几何先验与稠密前馈预测相结合提供了有原则的机制，所产生的重建既几何一致又空间完整，能够恢复精细结构并填补无纹理区域的空缺。仅在 ScanNet++ 上使用 VGGT 的预测结果训练，GGPT 即可跨架构、跨数据集泛化，在域内与域外设置下均大幅优于最优的前馈三维重建模型。
英文原文摘要 1385 字符
Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limited fine-grained accuracy due to the absence of explicit multi-view constraints. We introduce the Geometry-Grounded Point Transformer (GGPT), a framework that augments feed-forward reconstruction with reliable sparse geometric guidance. We first propose an improved Structure-from-Motion pipeline based on dense feature matching and lightweight geometric optimisation to efficiently estimate accurate camera poses and partial 3D point clouds from sparse input views. We propose a geometry-guided 3D point transformer that refines dense point maps under explicit partial-geometry supervision using an optimised guidance encoding. Extensive experiments demonstrate that our method provides a principled mechanism for integrating geometric priors with dense feed-forward predictions, producing reconstructions that are both geometrically consistent and spatially complete, recovering fine structures and filling gaps in textureless areas.Trained solely on ScanNet++ with VGGT predictions, GGPT generalises across architectures and datasets, substantially outperforming state-of-the-art feed-forward 3D reconstruction models in both in-domain and out-of-domain settings.