Research map / 3D vision / Depth and stereo
Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction
Frano Rajič, Yutong Chen, Haofei Xu, Zador Pataki, Marc Pollefeys, Siyu Tang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Scaffold3D, which conditions feed-forward pointmap prediction on SfM poses and sparse 3D points to improve multi-view 3D reconstruction in sparse and low-overlap settings.
Problem
Feed-forward multi-view 3D reconstruction models are fast but often imprecise or globally inconsistent across views, especially with sparse views and low overlap.
Approach
Uses structure-from-motion camera poses and sparse 3D points as a geometric scaffold that conditions pointmap prediction, propagating globally consistent SfM geometry into the feed-forward model.
Closest papers by meaning
- Light3R-SfM: Towards Feed-forward Structure-from-Motion (CVPR 2025 · similarity 0.88)
- Multi-view Reconstruction via SfM-guided Monocular Depth Estimation (CVPR 2025 · similarity 0.88)
- MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025 · similarity 0.88)
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images (CVPR 2025 · similarity 0.88)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.87)
- Dense-SfM: Structure from Motion with Dense Consistent Matching (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
