cs.CVNov 17, 2026

Refin3R: Geometry-Guided Refinement for Feed-Forward 3D Reconstruction

Authors: Jongmin Lee, Jaeyeong Kim, Seungryong Kim

Organizations: KAIST AI

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. GGPT: Geometry Grounded Point Transformer

    Mar 11, 2026Yutong Chen, Yiming Wang, Xucong Zhang +2Sparse-View 3D ReconstructionFeed-Forward 3D Reconstruction

  2. Glob3R: Global Structure-from-Motion with 3D Foundation Models

    Jul 10, 2026Junyuan Deng, Heng Li, Kejie Qiu +7Bundle AdjustmentMulti-View 3D Reconstruction

  3. PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

    Jul 2, 2026Haofei Xu, Rundi Wu, Philipp Henzler +7Diffusion TransformerMonocular 3D Reconstruction