← 研踪 PaperTrailarXiv:2611.23051 · v1
Refin3R: Geometry-Guided Refinement for Feed-Forward 3D Reconstruction
首次提交 2026-11-18 00:46
版本更新 2026-11-18 00:46
雷达观测 2026-11-18 16:38
摘要
Feed-forward 3D reconstruction models predict dense point maps from multiple images in a single pass. Without explicit geometric constraints, however, their predictions are often inconsistent across views and lack fine-grained precision. Recent methods incorporate geometric priors such as camera pose or depth, but use them merely as auxiliary inputs, process each view independently, or refine the geometry only where the priors are available. We present Refin3R, which refines feed-forward point maps with Structure-from-Motion (SfM) points, propagating SfM geometry over the image grid. In its dual-branch architecture, a 2D branch extends SfM geometry beyond its coverage using geometry-aware backbone features, while a 3D branch reasons over the SfM points of all views, capturing multi-view structure that the image grid alone cannot represent. The two branches exchange information bidirectionally to jointly refine each view, yielding dense and accurate point maps. Across ScanNet++, ETH3D, Tanks\&Temples, and out-of-domain human and surgical scenes, Refin3R consistently outperforms feed-forward and geometry-guided methods in point map accuracy while running faster than the strongest geometry-guided baseline.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-18 00:46 · 最新观测版本
Refin3R: Geometry-Guided Refinement for Feed-Forward 3D Reconstruction
Feed-forward 3D reconstruction models predict dense point maps from multiple images in a single pass. Without explicit geometric constraints, however, their predictions are often inconsistent across views and lack fine-grained precision. Recent methods incorporate geometric priors such as camera pose or depth, but use them merely as auxiliary inputs, process each view independently, or refine the geometry only where the priors are available. We present Refin3R, which refines feed-forward point maps with Structure-from-Motion (SfM) points, propagating SfM geometry over the image grid. In its dual-branch architecture, a 2D branch extends SfM geometry beyond its coverage using geometry-aware backbone features, while a 3D branch reasons over the SfM points of all views, capturing multi-view structure that the image grid alone cannot represent. The two branches exchange information bidirectionally to jointly refine each view, yielding dense and accurate point maps. Across ScanNet++, ETH3D, Tanks\&Temples, and out-of-domain human and surgical scenes, Refin3R consistently outperforms feed-forward and geometry-guided methods in point map accuracy while running faster than the strongest geometry-guided baseline.
查看此版本解读 →查看此版本原文 ↗